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. 102982
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of cuisine

    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
     Anſ
    -0.50
    bentar
    -0.47
     Independiente
    -0.47
     poiv
    -0.46
     gouver
    -0.46
    ghest
    -0.45
    יתוף
    -0.45
     PP
    -0.45
     Dew
    -0.44
    Thé
    -0.43
    POSITIVE LOGITS
     cuisine
    1.00
    Cuisine
    0.99
    cuisine
    0.91
     Cuisine
    0.91
     cuisines
    0.75
     Culinary
    0.57
     culinary
    0.56
    iculture
    0.55
     kuliner
    0.54
     surla
    0.54
    Activations Density 0.003%

    No Known Activations