© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11651
    Prev
    Next
    INDEX
    Explanations

    hierarchical structure and coding elements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.67
    AntiForgeryToken
    -0.65
    LLocation
    -0.65
    derung
    -0.63
    endpush
    -0.61
     GenerationType
    -0.60
    Personendaten
    -0.59
    oa̍t
    -0.59
    ApiRequest
    -0.58
    atial
    -0.57
    POSITIVE LOGITS
     menu
    3.23
    menu
    2.88
     Menu
    2.74
    Menu
    2.61
     MENU
    2.32
     menus
    2.28
    MENU
    2.18
    菜单
    2.09
     menú
    2.04
     меню
    1.97
    Activations Density 0.151%

    No Known Activations