© 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. 20-GEMMASCOPE-RES-131K
    11. 42618
    Prev
    Next
    INDEX
    Explanations

    semicolon characters in code snippets

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

    semicolon; code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    httphttps
    -0.96
    المناصب
    -0.89
    ftagPool
    -0.86
     pinulongan
    -0.76
    الدراسه
    -0.74
    mpagne
    -0.73
     незавершена
    -0.73
    AddTagHelper
    -0.72
    aarrggbb
    -0.72
    transQ
    -0.71
    POSITIVE LOGITS
    toPromise
    0.28
    __':
    0.28
     behoort
    0.28
     araña
    0.27
     dessus
    0.26
    ;
    0.26
    .*;
    0.25
    NSError
    0.24
    Slf
    0.23
     perros
    0.23
    Activations Density 0.002%

    No Known Activations