© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4163
    Prev
    Next
    INDEX
    Explanations

    culinary instructions and specific cooking terms

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

    Ingredients (seafood, vegetables, nuts)

    np_acts-logits-general · gemini-2.0-flash

    ingredients for cooking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.37
    Geplaatst
    -0.36
     незавершена
    -0.35
    atschappij
    -0.33
     contour
    -0.32
    出一个
    -0.32
     Cera
    -0.31
    (:,:,
    -0.31
     build
    -0.31
     built
    -0.31
    POSITIVE LOGITS
    ніципалі
    0.69
    TagMode
    0.56
    EDEFAULT
    0.54
    erçe
    0.53
    OGND
    0.53
    はじめに
    0.48
    GIVEREF
    0.47
    Insee
    0.47
    plish
    0.47
    jewelry
    0.47
    Activations Density 0.174%

    No Known Activations