© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10941
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and their results

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

    special formatting elements like tables, code, citations, and document structure markers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    commodations
    -0.55
     vooz
    -0.52
    ſſung
    -0.52
    iſche
    -0.52
    issors
    -0.52
     PropTypes
    -0.50
    <unused51>
    -0.50
    [@BOS@]
    -0.50
    <pad>
    -0.50
    <unused8>
    -0.50
    POSITIVE LOGITS
     upto
    0.48
    upto
    0.46
    noOf
    0.45
    pushFollow
    0.44
    providedIn
    0.42
     برانيه
    0.42
    NoOf
    0.42
     snippetHide
    0.39
    DrawerToggle
    0.38
    Numerology
    0.38
    Activations Density 0.137%

    No Known Activations