© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 125359
    Prev
    Next
    INDEX
    Explanations

    instances of dining-related concepts and etiquette

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

    dining with others/etiquette

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Willy
    -0.48
    Parcelize
    -0.47
    endregion
    -0.47
    Rupert
    -0.46
     Heck
    -0.46
    Voltar
    -0.46
     Kapp
    -0.45
    ECTOR
    -0.44
    Chars
    -0.44
     wer
    -0.44
    POSITIVE LOGITS
     Dining
    1.09
     dining
    1.04
    Dining
    0.99
    dining
    0.95
     Dine
    0.95
    Dine
    0.93
     dined
    0.91
     dine
    0.87
     Diner
    0.77
     diners
    0.73
    Activations Density 0.002%

    No Known Activations