© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5423
    Prev
    Next
    INDEX
    Explanations

    parentheses and numerical data related to calculations or measurements

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

    Numbers or percentages inside parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers in parentheses

    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-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
     stran
    -0.50
    saraba
    -0.43
     st
    -0.39
    gh
    -0.38
    ссий
    -0.37
    tal
    -0.36
     tinh
    -0.36
    fek
    -0.34
    ding
    -0.34
    izarse
    -0.33
    POSITIVE LOGITS
    HideFlags
    0.86
     '\\;'
    0.86
    SharedCtor
    0.82
    InjectAttribute
    0.82
    DoubleQuotes
    0.81
    titleMargin
    0.79
    sizeCache
    0.76
    encodeWith
    0.76
    UnknownFields
    0.76
    verwijspagina
    0.74
    Activations Density 0.276%

    No Known Activations