mlsanityData to 7 Oct 2026

An Analysis of Residual-Stream Geometry Across Transformer Depth

arXiv 2607.18348 ↗First posted 20 Jul 2026cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a transition-centred geometric analysis of transformer residual streams. Relative displacement measures how far representations move between consecutive layers, and orthogonal Procrustes analysis separates each transition into a rigid rotation and a non-rigid residual. Across six instruction-tuned models, on code generation and cross-lingual translation, these measurements reveal reproducible depth regularities. Relative displacement is strongly layer-dependent; typically larger early and late, with a quieter middle third; and nearly invariant across conditions within each model. Rotation magnitude is nearly constant across depth, while Procrustes residual and angle concentration remain depth-modulated, with residual peaking at the final transition. During generation, non-English targets show larger final-layer displacement and residual than English targets. We present these as descriptive geometric regularities, not as measures of computational effort or causal explanations. The contribution is a measurement framework for residual-stream transitions and evidence that, in the settings studied here, depth curves are model-dependent and largely condition-stable.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 20 Jul 2026.

Builds on

19 of 29 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  3. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  4. 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
  5. 2023Eliciting Latent Predictions from Transformers with the Tuned Lenscited by 579
  6. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 275
  7. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformerscited by 223
  8. 2019Emerging Cross-lingual Structure in Pretrained Language Modelscited by 180
  9. 2022The Geometry of Multilingual Language Model Representationscited by 94
  10. 2025Do Multilingual LLMs Think In English?cited by 75
  11. 2025Do Language Models Use Their Depth Efficiently?cited by 48
  12. 2025The Geometry of Reasoning: Flowing Logics in Representation Spacecited by 21
7 more
  1. 2025The Intrinsic Dimension of Prompts in Internal Representations of Large Language Modelscited by 17
  2. 2023Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networkscited by 12
  3. 2026Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoningcited by 9
  4. 2024The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networkscited by 8
  5. 2026Context Structure Reshapes the Representational Geometry of Language Modelscited by 6
  6. 2025Unraveling the geometry of visual relational reasoningcited by 3
  7. 2026Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.