© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5168
    Prev
    Next
    INDEX
    Explanations

    references to cooking utensils, specifically pans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ładka
    -0.34
    PN
    -0.33
    ustes
    -0.33
    těte
    -0.32
    Punk
    -0.32
    queryInterface
    -0.32
     Punk
    -0.32
    providedIn
    -0.31
    tées
    -0.31
     PUN
    -0.31
    POSITIVE LOGITS
     pan
    3.11
     Pan
    2.41
    Pan
    2.38
    pan
    2.23
     PAN
    1.77
     pans
    1.67
    PAN
    1.55
     panning
    1.52
    pans
    1.31
     Pancha
    1.24
    Activations Density 0.038%

    No Known Activations