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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 561
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific or technical terms

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

    references to exclusive content and subscriptions

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

    advance, begin, enumerate

    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
     FetchType
    -0.83
    Искәрмәләр
    -0.74
    aarrggbb
    -0.67
    ✭✭
    -0.66
     ✭✭
    -0.59
    PreExecute
    -0.58
    HtmlAttribute
    -0.58
     VIAF
    -0.57
    modb
    -0.56
     truer
    -0.54
    POSITIVE LOGITS
     
    0.56
    enumerate
    0.56
     recognition
    0.53
     advance
    0.53
     advances
    0.52
    enumi
    0.51
    advance
    0.49
    begin
    0.48
    extAlignment
    0.48
    rump
    0.47
    Activations Density 0.003%

    No Known Activations