© 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. 10583
    Prev
    Next
    INDEX
    Explanations

    text elements related to mathematical or computational discussions, particularly symbols and notations

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

    Code, comments, and file paths

    np_acts-logits-general · gemini-2.0-flash

    code documentation and internationalization

    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
    IntoConstraints
    -0.72
     AssemblyCulture
    -0.67
    verwijspagina
    -0.60
    ArrowToggle
    -0.59
     Parcelable
    -0.58
    ajevo
    -0.57
    bcryptjs
    -0.57
    LLocation
    -0.57
    extAlignment
    -0.57
    gypti
    -0.57
    POSITIVE LOGITS
    Geplaatst
    0.56
     Pied
    0.50
    ніципалі
    0.49
    exports
    0.46
    fao
    0.46
    ַח
    0.45
     fait
    0.45
    [toxicity=0]
    0.44
     //
    0.43
    WebControls
    0.43
    Activations Density 0.286%

    No Known Activations