Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31525
    Prev
    Next
    INDEX
    Explanations

    references to dining experiences and etiquette

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

    dining etiquette and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.57
    SequentialGroup
    -0.53
     surla
    -0.50
    setVerticalGroup
    -0.46
    abcdefghijklmnop
    -0.44
    BIÉN
    -0.43
    delwed
    -0.42
    ConstraintMaker
    -0.42
     autorytatywna
    -0.41
    ürtel
    -0.41
    POSITIVE LOGITS
     dining
    1.13
     Dining
    1.09
    Dining
    1.03
    dining
    0.98
     dine
    0.97
    Dine
    0.96
     dined
    0.93
     diners
    0.91
     Dine
    0.91
     Dinner
    0.80
    Activations Density 0.010%

    No Known Activations