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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9264
    Prev
    Next
    INDEX
    Explanations

    specific actions or behaviors related to social interactions and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.75
    NonQuery
    -0.73
    Portale
    -0.73
     Shakspeare
    -0.71
     unknownFields
    -0.70
    IndentedString
    -0.68
     للمعارف
    -0.66
     Shaksp
    -0.65
    ThroughAttribute
    -0.64
     mxArray
    -0.63
    POSITIVE LOGITS
     identify
    1.03
     determine
    0.98
     identifying
    0.95
     Identify
    0.94
     determining
    0.91
     identified
    0.87
    Identify
    0.84
     Determine
    0.84
     assess
    0.83
     determined
    0.83
    Activations Density 0.323%

    No Known Activations