© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7909
    Prev
    Next
    INDEX
    Explanations

    JavaScript code that involves the Gulp task runner and its associated plugins or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.97
     مشين
    -0.90
    TagMode
    -0.87
    ScopeManager
    -0.84
     newOwner
    -0.82
    FunctionFlags
    -0.82
    ftagPool
    -0.78
    expandindo
    -0.78
    DeleteBehavior
    -0.76
    InputBorder
    -0.74
    POSITIVE LOGITS
    zzleHttp
    0.52
    #![
    0.51
    libft
    0.47
    ::$
    0.45
     Ethel
    0.45
     minimalistic
    0.43
    жника
    0.42
     tapa
    0.41
     vader
    0.41
    IBA
    0.40
    Activations Density 0.281%

    No Known Activations