© 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. 6878
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals, organizations, and product names related to social topics

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

    Appears before names, titles, or organizations

    np_acts-logits-general · gemini-2.0-flash

    Candida, Victor, Massachusetts

    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
    ്യ
    -0.59
    drž
    -0.56
    ptonshire
    -0.53
    ziell
    -0.53
    utica
    -0.51
    InBytes
    -0.49
    ALS
    -0.49
    ,\,\
    -0.48
    y
    -0.48
    PDATE
    -0.48
    POSITIVE LOGITS
    UpInside
    0.73
    setupUi
    0.72
     مشين
    0.71
    IntoConstraints
    0.70
    UnusedPrivate
    0.70
     onOptions
    0.69
     Audiodateien
    0.69
     vPvB
    0.68
     linkovi
    0.67
    TypedDataSet
    0.67
    Activations Density 0.510%

    No Known Activations