© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 745
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and numeric expressions

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

    mathematical expressions and symbols related to vector notation

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

    n symbols and formulas

    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
    RUnlock
    -0.69
     nomination
    -0.68
     Wikimedijinoj
    -0.66
     HasFactory
    -0.64
    tonsoft
    -0.64
    ScopeManager
    -0.63
     estekak
    -0.63
     notices
    -0.63
     notice
    -0.62
    stateProvider
    -0.62
    POSITIVE LOGITS
     N
    0.86
     n
    0.76
    N
    0.58
    Nc
    0.52
    setN
    0.52
    ɴ
    0.50
    getN
    0.50
    ntr
    0.49
    Nr
    0.49
     Nr
    0.49
    Activations Density 0.155%

    No Known Activations