© 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. 38-GEMMASCOPE-RES-16K
    6. 8902
    Prev
    Next
    INDEX
    Explanations

    actions and interactions involving clothing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leuth
    -0.49
     jspb
    -0.47
    ousands
    -0.47
    cloudfront
    -0.46
    #![
    -0.46
    燃烧
    -0.45
     يتيمه
    -0.45
    Rüyada
    -0.44
     useParams
    -0.43
    enetrable
    -0.43
    POSITIVE LOGITS
     hurried
    0.65
     retrieved
    0.64
     hurry
    0.60
     walked
    0.59
     grabbed
    0.58
     heading
    0.58
     grab
    0.57
     hurrying
    0.56
     upstairs
    0.55
     headed
    0.54
    Activations Density 0.401%

    No Known Activations