© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128734
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, and specific references related to academic or professional contexts

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

    German, Italian, Japanese, and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ey
    -0.85
    ry
    -0.81
    yyyy
    -0.77
    y
    -0.77
    yy
    -0.72
    ety
    -0.69
    yny
    -0.69
    ay
    -0.69
    dy
    -0.68
    yyy
    -0.67
    POSITIVE LOGITS
     فريبيس
    0.57
     Gohan
    0.54
     raiſ
    0.54
    fahan
    0.53
     Crusoe
    0.53
     tslint
    0.52
     mapStateToProps
    0.52
     UIFont
    0.51
    UIFont
    0.51
     tilbud
    0.49
    Activations Density 0.305%

    No Known Activations