© 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. 14-GEMMASCOPE-RES-16K
    11. 7256
    Prev
    Next
    INDEX
    Explanations

    instances of cooking and culinary activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veratrol
    -0.57
    asteroide
    -0.50
    ᅠ
    -0.48
     benefit
    -0.48
    alsey
    -0.47
     lượt
    -0.47
     Sharpe
    -0.46
    posedge
    -0.45
     Factor
    -0.44
     Rand
    -0.44
    POSITIVE LOGITS
    Cook
    1.24
    cook
    1.16
     Cook
    1.16
    Cooking
    1.13
     COOK
    1.13
     cook
    1.12
     cooking
    1.09
     Cooking
    1.09
    cooking
    1.08
    cooked
    1.00
    Activations Density 0.075%

    No Known Activations