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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6588
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ayı
    -0.35
    bigsqcup
    -0.33
     tillegg
    -0.32
     Wahrnehmung
    -0.32
    ését
    -0.32
    ₡
    -0.32
     obiekt
    -0.32
     suelos
    -0.31
    enschap
    -0.31
     relleno
    -0.31
    POSITIVE LOGITS
    HasForeignKey
    0.50
    DispatchToProps
    0.50
    новниш
    0.50
    addContainerGap
    0.50
    ViewFeatures
    0.49
    RTLI
    0.48
     ExecuteAsync
    0.47
    principalColumn
    0.47
    aarrggbb
    0.47
    ArrowToggle
    0.47
    Activations Density 0.482%

    No Known Activations