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. 24-GEMMASCOPE-RES-16K
    6. 4529
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to food and cooking

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

    food or eating

    np_acts-logits-general · gemini-2.0-flash

    food, eating, and meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جغرافيا
    -0.45
    chromedriver
    -0.45
    出版年
    -0.45
    pernicus
    -0.44
    RectangleBorder
    -0.42
    adecimal
    -0.42
    virons
    -0.42
     loan
    -0.41
     smallpox
    -0.41
    ICIAL
    -0.41
    POSITIVE LOGITS
     food
    1.95
     eating
    1.92
     meals
    1.88
     meal
    1.87
     culinary
    1.79
     cuisine
    1.74
     eat
    1.69
     dining
    1.69
     Food
    1.68
    Food
    1.67
    Activations Density 0.704%

    No Known Activations