© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking methods and ingredient preparations

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

    cooking or frying

    np_acts-logits-general · gemini-2.0-flash

    cooking, browning, frying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habet
    -0.55
     peregr
    -0.49
    டைய
    -0.49
    ETRY
    -0.48
     Sä
    -0.48
    гинал
    -0.47
     balas
    -0.47
    西瓜
    -0.46
     purpure
    -0.46
    عار
    -0.45
    POSITIVE LOGITS
     cooking
    1.60
     cook
    1.55
     cooked
    1.44
    cooking
    1.42
     COOK
    1.41
     cooks
    1.37
    Cook
    1.37
    cook
    1.35
     frying
    1.34
     Cooking
    1.33
    Activations Density 0.143%

    No Known Activations