© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105373
    Prev
    Next
    INDEX
    Explanations

    references to emotions and personal connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Contractions (especially "'s", "'ll", "'t") and connecting words that form meaningful phrases in informal online text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    setVerticalGroup
    -0.74
    UrlResolution
    -0.61
    tagHelperRunner
    -0.60
    DockStyle
    -0.58
    rungsseite
    -0.57
     MainAxisSize
    -0.51
     CreateTagHelper
    -0.51
     EconPapers
    -0.48
     Pumps
    -0.47
     становника
    -0.47
    POSITIVE LOGITS
    <_>
    0.41
     المعيارى
    0.38
    closeConnection
    0.37
     információk
    0.36
    Heya
    0.35
    Liebe
    0.34
     замет
    0.34
     acom
    0.34
    ค่ะ
    0.33
     angew
    0.33
    Activations Density 0.058%

    No Known Activations