© 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. 8221
    Prev
    Next
    INDEX
    Explanations

    food-related terms, specifically those associated with Indian and vegetarian dishes

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

    Reviews or descriptions of food/dishes

    np_acts-logits-general · gemini-2.0-flash

    authentic Chinese Korean food

    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
    saraba
    -0.56
     BitmapFactory
    -0.50
    脚注の使い方
    -0.48
     coffee
    -0.44
    isDebugEnabled
    -0.44
    ciutto
    -0.43
     norman
    -0.43
    🍩
    -0.43
    usercontent
    -0.43
     Brewers
    -0.43
    POSITIVE LOGITS
    authentic
    0.73
    ThroughAttribute
    0.72
    Authentic
    0.72
    IVEREF
    0.71
    +#+#
    0.70
     authentic
    0.68
     Authentic
    0.68
     takeout
    0.68
     Chinatown
    0.67
     ExecuteAsync
    0.65
    Activations Density 0.142%

    No Known Activations