© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8604
    Prev
    Next
    INDEX
    Explanations

    culinary terms and dish ingredients

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

    specific food dishes and ingredients mentioned in restaurant reviews.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    descriptions of prepared food dishes, particularly when they include specific ingredients, cooking methods, or menu items.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of specific meat and seafood dishes with their cooking preparations in restaurant or menu contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    </thead>
    -0.38
     betweenstory
    -0.37
     frukt
    -0.35
     ganchillo
    -0.34
     cérami
    -0.34
     hidráulica
    -0.32
     compresión
    -0.32
     colectiva
    -0.31
     Economía
    -0.31
     cerámica
    -0.31
    POSITIVE LOGITS
     steaks
    0.66
    Autoritní
    0.62
     risotto
    0.58
    titleMargin
    0.56
     Strips
    0.56
     bistro
    0.56
     tavern
    0.55
     steak
    0.55
     martini
    0.55
    :✨
    0.54
    Activations Density 0.117%

    No Known Activations