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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13115
    Prev
    Next
    INDEX
    Explanations

    cooking-related activities and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.69
     تانيه
    -0.66
     فريبيس
    -0.64
    حياتها
    -0.64
    новништво
    -0.63
    AsUp
    -0.62
    RegressionTest
    -0.56
    ьаж
    -0.56
    حياته
    -0.53
    DllImport
    -0.52
    POSITIVE LOGITS
     recipes
    1.03
     Recipes
    0.89
     recipe
    0.88
    recipes
    0.86
    Recipes
    0.81
     RECIPES
    0.77
    recipe
    0.77
     cook
    0.74
     cooks
    0.73
     Recipe
    0.73
    Activations Density 0.155%

    No Known Activations