© 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. 20-GEMMASCOPE-RES-16K
    6. 5271
    Prev
    Next
    INDEX
    Explanations

    terms related to cooking and culinary activities

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

    cooking and kitchen-related terms and actions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Sharpe
    -0.51
    idget
    -0.47
    hdys
    -0.46
     Weiss
    -0.46
     Garza
    -0.45
    istiwa
    -0.45
    asteroide
    -0.45
     Straus
    -0.44
    argli
    -0.44
    alsey
    -0.44
    POSITIVE LOGITS
    Cook
    0.92
    cook
    0.84
     Cook
    0.84
    Cooking
    0.78
     COOK
    0.78
     cook
    0.76
     Cooked
    0.75
     Cooking
    0.73
    cooked
    0.70
    cooking
    0.69
    Activations Density 0.081%

    No Known Activations