© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12704
    Prev
    Next
    INDEX
    Explanations

    references to nuts and related ingredients in food contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hib
    -0.38
    ího
    -0.34
    bebasan
    -0.34
    libft
    -0.32
     Abel
    -0.30
    inkt
    -0.30
     gradient
    -0.30
     Baca
    -0.29
     Donovan
    -0.29
    getreten
    -0.29
    POSITIVE LOGITS
     nut
    1.91
     nuts
    1.91
     Nuts
    1.73
    Nuts
    1.71
    nuts
    1.69
     Nut
    1.58
    Nut
    1.55
    nut
    1.52
     NUT
    1.41
     walnuts
    1.38
    Activations Density 0.230%

    No Known Activations