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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22467
    Prev
    Next
    INDEX
    Explanations

    references to family meals and communal eating experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     חיצוניים
    -0.63
    ביוגרפיה
    -0.49
    ulli
    -0.47
     Lib
    -0.46
    umid
    -0.46
    illar
    -0.46
    uens
    -0.46
    hode
    -0.45
    subtype
    -0.45
    SOUNDBITE
    -0.44
    POSITIVE LOGITS
     dining
    0.69
     meal
    0.66
     meals
    0.65
     dinner
    0.63
     diners
    0.61
     Meals
    0.59
     Meal
    0.59
    Dinner
    0.57
     Dinner
    0.57
     diner
    0.57
    Activations Density 0.024%

    No Known Activations