Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73466
    Prev
    Next
    INDEX
    Explanations

    numerical data and tabular representations related to scientific or statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical, statistical, and programming syntax elements used in scientific documentation, particularly punctuation, operators, and numeric formatting in tables, code blocks, and equations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.63
     autorytatywna
    -0.57
     AssemblyProduct
    -0.55
     propOrder
    -0.55
    TypedDataSet
    -0.54
    webElementGuid
    -0.52
    BeginContext
    -0.49
    PerformLayout
    -0.48
    archiviato
    -0.48
    Välislingid
    -0.47
    POSITIVE LOGITS
     integrated
    0.42
     Herrmann
    0.41
     Utilizamos
    0.40
     Cientí
    0.40
     Kelurahan
    0.38
    cityId
    0.38
     integrado
    0.38
    propertyName
    0.38
    integrated
    0.38
     oreille
    0.37
    Activations Density 0.461%

    No Known Activations