Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 143
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and their descriptions in various contexts

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

    expressions and descriptions related to facial expressions and gazes.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vikipedi
    -0.63
    pahan
    -0.62
     Jefus
    -0.61
    felves
    -0.61
    inderella
    -0.60
    IBAction
    -0.60
    scription
    -0.59
    aarrggbb
    -0.59
    Véase
    -0.58
     tiện
    -0.58
    POSITIVE LOGITS
     MessageBoxIcon
    0.63
    WebServlet
    0.60
     expression
    0.60
     stare
    0.58
    ControllerAdvice
    0.56
     staring
    0.56
     countenance
    0.54
     face
    0.54
    表情
    0.54
     smile
    0.53
    Activations Density 0.142%

    No Known Activations