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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2969
    Prev
    Next
    INDEX
    Explanations

    references to food options or menu items

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

    Restaurant reviews or menus

    np_acts-logits-general · gemini-2.0-flash

    food items and menus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tvguidetime
    -0.73
    IntoConstraints
    -0.69
    adə
    -0.65
    reportWebVitals
    -0.64
     AssemblyCulture
    -0.63
    ciclop
    -0.63
     Hospitals
    -0.61
    DeleteBehavior
    -0.60
     recul
    -0.60
    Rüyada
    -0.60
    POSITIVE LOGITS
     menu
    1.12
     specials
    0.80
    menu
    0.76
     menus
    0.72
     Menu
    0.71
     menú
    0.70
    Menu
    0.65
     меню
    0.64
     daily
    0.63
     servem
    0.63
    Activations Density 0.104%

    No Known Activations