© 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. 12-GEMMASCOPE-RES-16K
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of cooking or preparing food, particularly with a focus on igniting or combining ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     c
    -0.44
    ватель
    -0.40
     patri
    -0.39
    リック
    -0.39
    pf
    -0.39
    Fond
    -0.39
    ca
    -0.37
     C
    -0.36
    Write
    -0.36
    وانی
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    1.06
    новниш
    0.85
     estekak
    0.75
    verwijspagina
    0.75
    QMetaType
    0.73
    enderror
    0.72
     StatelessWidget
    0.71
    EndProject
    0.71
    endpush
    0.70
    المناصب
    0.69
    Activations Density 0.648%

    No Known Activations