© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15959
    Prev
    Next
    INDEX
    Explanations

    cooking-related terms and instructions

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

    cooking instructions and recipe preparation steps.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ब्रेकडाउन
    -0.45
    GEBURTSDATUM
    -0.41
    ollectionView
    -0.41
    dersfield
    -0.40
     bureaus
    -0.40
    Coords
    -0.39
    ghans
    -0.39
    endmodule
    -0.39
     Må
    -0.38
     bureau
    -0.38
    POSITIVE LOGITS
     frying
    0.81
     sauté
    0.73
     saute
    0.66
     skillet
    0.63
     сковоро
    0.61
     tossing
    0.59
     sartén
    0.57
     sizzling
    0.56
     fry
    0.56
     pan
    0.56
    Activations Density 0.093%

    No Known Activations