Work

ELENS: Embedding Lens — A Geometric and Statistical Framework for Investigating Internal Representations, Activation Dynamics, and Candidate Harmony Directions in Gemma Architectures

Year: 2026
Type: article
Abstract: Research proposal introducing ELENS (Embedding Lens), a proposed interpretability and measurement framework for investigating internal representations in embedding models, with particular emphasis on EmbeddingGemma 2 and the Gemma model family. The proposal combines layer-wise activation extraction, geometric analysis, statistical characterization, sparse feature investigation, and controlled causal intervention. It also outlines the unverified Harmony Axis hypothesis, which asks whether the mathematical inverse of a previously identified pain-related activation direction produces an independently measurable representational or functional state. No experimental results or validated Harmony Axis are claimed. Architecture descriptions are cross-referenced to the technical report and official model card.
Language: English
Open Access status: green
OpenAlex ID: W7235300826
FWCI:
Cites:
Cited by:
Related to: 10