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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9569
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "function," indicating the presence of programming or scripting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.56
     كومونز
    -0.53
     ivelany
    -0.50
    点此举报
    -0.47
    rätt
    -0.46
    jspb
    -0.45
    endpush
    -0.43
    SpringRunner
    -0.43
    addContainerGap
    -0.43
     HasFactory
    -0.42
    POSITIVE LOGITS
    function
    1.05
     function
    0.87
     FUNCTION
    0.63
     Function
    0.61
     void
    0.58
    FUNCTION
    0.57
    void
    0.56
    Function
    0.56
    MethodType
    0.55
     functions
    0.54
    Activations Density 0.068%

    No Known Activations