© 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. 31-GEMMASCOPE-RES-131K
    11. 8349
    Prev
    Next
    INDEX
    Explanations

    elements related to document structure in a programming context

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

    UI components and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     дописавши
    -0.54
    ScopeManager
    -0.49
    httphttps
    -0.48
    MLLoader
    -0.47
    encodeWith
    -0.47
    ніципалі
    -0.44
    AddHtmlAttribute
    -0.43
    quiao
    -0.42
     BorderSide
    -0.42
    rawDesc
    -0.41
    POSITIVE LOGITS
    centralwidget
    0.50
     title
    0.49
    AsUp
    0.44
     titre
    0.43
     título
    0.42
     Titre
    0.42
    maketitle
    0.42
     indisponible
    0.41
    avajillas
    0.41
     jugement
    0.41
    Activations Density 0.002%

    No Known Activations