© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10569
    Prev
    Next
    INDEX
    Explanations

    mentions of kitchens and kitchen-related items or features

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

    "kitchen"

    np_acts-logits-general · gemini-2.0-flash

    kitchen related items/actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    новниш
    -0.54
    WaitGroup
    -0.51
    gdx
    -0.50
     Byers
    -0.47
    üğü
    -0.47
    holtz
    -0.46
     disambiguazione
    -0.46
    AndroidJUnit
    -0.46
     Hurst
    -0.45
    τής
    -0.44
    POSITIVE LOGITS
     kitchen
    0.81
    kitchen
    0.77
    Kitchen
    0.76
     Kitchen
    0.71
     kitchens
    0.69
     KITCHEN
    0.66
     Kitchens
    0.63
     kitchenette
    0.59
    厨房
    0.55
    キッチン
    0.54
    Activations Density 0.074%

    No Known Activations