© 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. 85987
    Prev
    Next
    INDEX
    Explanations

    text related to responses and reactions to specific events or statements

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

    in response to

    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
    ValueStyle
    -0.52
     незавершена
    -0.47
    bitField
    -0.45
    AndPassword
    -0.44
     Informações
    -0.37
    //*[@
    -0.37
     péri
    -0.37
    fortawesome
    -0.36
     CWE
    -0.36
    ühnen
    -0.36
    POSITIVE LOGITS
     response
    1.29
     responses
    1.08
     respond
    1.08
     Response
    1.03
    response
    1.02
     responds
    1.02
     responded
    1.01
     RESPONSE
    1.01
     respuesta
    0.98
     responding
    0.98
    Activations Density 0.086%

    No Known Activations