© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and semicolons

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

    code context with method calls

    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
    TagMode
    -0.86
     ddelwed
    -0.69
     مرئيه
    -0.62
     كومونز
    -0.61
     ſehr
    -0.60
    niſſe
    -0.60
     erſt
    -0.60
    TypedDataSet
    -0.60
     uLocal
    -0.60
    Hentet
    -0.59
    POSITIVE LOGITS
     JpaRepository
    0.37
     británica
    0.32
    principalColumn
    0.31
     face
    0.29
     <=",
    0.29
     extranjera
    0.28
    gänge
    0.28
    endaft
    0.28
    новниш
    0.27
     гарни
    0.27
    Activations Density 0.000%

    No Known Activations