© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 3222
    Prev
    Next
    INDEX
    Explanations

    function declarations and instantiations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ä
    -0.54
     AssemblyCulture
    -0.46
    ftagPool
    -0.44
    CreateInfo
    -0.43
    édrale
    -0.43
    setCell
    -0.41
    Schemes
    -0.40
     files
    -0.39
     schemes
    -0.39
     vaut
    -0.39
    POSITIVE LOGITS
     שוליים
    0.88
    EndProject
    0.87
    ArgsConstructor
    0.87
     }}"></
    0.78
     ſmall
    0.75
     Baillargeon
    0.73
     raiſ
    0.71
    sizeCache
    0.71
     ProtoMessage
    0.71
     uſed
    0.70
    Activations Density 0.105%

    No Known Activations