© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1366
    Prev
    Next
    INDEX
    Explanations

    references to voting processes and electoral participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to popular voting and awards related to the science fiction community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    votes and voting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    iserie
    -0.49
     kohdetta
    -0.48
    AddTagHelper
    -0.48
     Medea
    -0.47
     ***!
    -0.47
     invariants
    -0.47
    hnia
    -0.47
    lenburg
    -0.47
    انجليز
    -0.47
     uintptr
    -0.46
    POSITIVE LOGITS
     vote
    2.98
     voting
    2.83
     votes
    2.81
    vote
    2.48
     Vote
    2.45
     Voting
    2.41
    Voting
    2.33
    Vote
    2.32
     voted
    2.31
     VOTE
    2.29
    Activations Density 0.217%

    No Known Activations