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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9911
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commitment
    -0.49
     noqa
    -0.45
     commit
    -0.42
     playmobil
    -0.40
    WillAppear
    -0.39
    abestanden
    -0.39
     Commitment
    -0.39
     Meksiku
    -0.39
     commitments
    -0.38
    SuppressMessage
    -0.38
    POSITIVE LOGITS
    setVerticalGroup
    0.56
     onPostExecute
    0.52
    ...}
    0.48
    MENAFN
    0.45
    jší
    0.45
    GETHER
    0.44
    Искәрмәләр
    0.44
    ylum
    0.42
    Condol
    0.42
    Externé
    0.41
    Activations Density 0.466%

    No Known Activations