Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16200
    Prev
    Next
    INDEX
    Explanations

    specific references to Huntington's disease and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cifix
    -0.87
     Swanson
    -0.83
    TypeDef
    -0.83
    //
    -0.82
     Đà
    -0.80
    nościo
    -0.79
     Monza
    -0.74
     Hartmann
    -0.73
     Fris
    -0.71
     Hima
    -0.71
    POSITIVE LOGITS
     Kro
    0.83
     Keating
    0.80
     Sku
    0.79
     Huntington
    0.78
    Devin
    0.77
     HasFactory
    0.77
     Gand
    0.75
     Cranston
    0.75
     Emanuel
    0.74
     plomb
    0.74
    Activations Density 2.072%

    No Known Activations