© 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. 27716
    Prev
    Next
    INDEX
    Explanations

    references to programming data structures and collections

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

    user input starters

    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
    aarrggbb
    -0.92
     nakalista
    -0.75
     createSlice
    -0.75
    WithIOException
    -0.74
     resourceCulture
    -0.74
     Wikimedijinoj
    -0.73
    SaveChangesAsync
    -0.72
     getItemId
    -0.71
    djangoproject
    -0.70
     AssemblyCulture
    -0.69
    POSITIVE LOGITS
     IList
    0.59
    SEVERE
    0.55
     ICollection
    0.53
     CHtml
    0.47
    IList
    0.47
    ollection
    0.47
    fristig
    0.32
    Lage
    0.31
    joy
    0.30
     toep
    0.30
    Activations Density 0.000%

    No Known Activations