© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12427
    Prev
    Next
    INDEX
    Explanations

    reviews and descriptions related to restaurant menus and food options

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

    menu options and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viitteet
    -0.55
    bcryptjs
    -0.45
     Communities
    -0.43
    Communities
    -0.42
    woosh
    -0.41
     bedankt
    -0.40
    communities
    -0.40
     fusca
    -0.40
     uncin
    -0.39
    вол
    -0.39
    POSITIVE LOGITS
     options
    0.88
     opciones
    0.73
     menu
    0.69
     offerings
    0.68
    options
    0.68
     opções
    0.67
     choices
    0.67
     Optionen
    0.65
     offering
    0.65
     option
    0.64
    Activations Density 0.025%

    No Known Activations