© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13032
    Prev
    Next
    INDEX
    Explanations

    data and statistics related to demographic breakdowns and distributions

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

    "Breakdown," "results," or "characteristics" tables

    np_acts-logits-general · gemini-2.0-flash

    statistical breakdown

    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
     leksikon
    -0.55
    umbra
    -0.52
    brainly
    -0.50
     offerts
    -0.50
    imread
    -0.50
    AppMethodBeat
    -0.48
    QMetaType
    -0.48
     écrits
    -0.48
     makeStyles
    -0.47
    最快更新
    -0.46
    POSITIVE LOGITS
     breakdown
    1.50
     breakdowns
    1.30
     Breakdown
    1.24
    breakdown
    1.23
    Breakdown
    1.17
     broken
    1.14
     desglose
    0.93
     break
    0.93
    broken
    0.91
     breaking
    0.88
    Activations Density 0.543%

    No Known Activations