© 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
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4275
    Prev
    Next
    INDEX
    Explanations

    specific references to education, personal belongings, and school-related logistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.66
     lèvres
    -0.61
     qualités
    -0.60
    uxxxx
    -0.60
    HtmlAttribute
    -0.60
    RectangleBorder
    -0.59
    addCriterion
    -0.59
    erschrank
    -0.59
    tangentMode
    -0.59
    haviors
    -0.59
    POSITIVE LOGITS
     calendars
    0.69
     refrigerators
    0.69
     fireplaces
    0.69
     dashboards
    0.68
     balconies
    0.64
     thermometers
    0.64
     backpacks
    0.63
     furnaces
    0.63
     Bibles
    0.63
     ladders
    0.63
    Activations Density 2.424%

    No Known Activations