© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 86775
    Prev
    Next
    INDEX
    Explanations

    specific names and titles, particularly those related to identity or designation

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

    jark matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Quo
    -0.57
    </table>
    -0.57
    akis
    -0.55
    <#
    -0.55
    googleapis
    -0.54
    Ще
    -0.51
    #>
    -0.50
     useNavigate
    -0.50
    Reveal
    -0.49
    enumii
    -0.49
    POSITIVE LOGITS
     Burt
    0.57
     désert
    0.56
     Berlín
    0.52
    art
    0.52
     prêtre
    0.52
    Irlande
    0.52
    useNewUrlParser
    0.52
     Arn
    0.51
     Ard
    0.50
    Burt
    0.50
    Activations Density 0.211%

    No Known Activations