© 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. 319
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly for structured data or mathematical results

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

    Mathematical or code-related expressions and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical variables and indices

    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
    /
    -0.49
    nter
    -0.43
    ("$.
    -0.41
    DropTable
    -0.40
    тен
    -0.40
     Mo
    -0.40
    usk
    -0.39
     more
    -0.39
     Wind
    -0.39
    setHorizontal
    -0.39
    POSITIVE LOGITS
    WebControls
    0.92
    TargetException
    0.86
     فريبيس
    0.85
    RectangleBorder
    0.85
     समीक्षाओं
    0.82
    EndContext
    0.82
     الحره
    0.80
     تضيفلها
    0.80
     חיצוניים
    0.78
    verwijspagina
    0.77
    Activations Density 1.037%

    No Known Activations