© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5354
    Prev
    Next
    INDEX
    Explanations

    food-related terms and descriptions, particularly focusing on ingredients and types of dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GeoNames
    -0.53
     praktijk
    -0.51
    xffffffff
    -0.50
    laient
    -0.49
    reactivex
    -0.48
    サート
    -0.47
    dracht
    -0.47
    braucher
    -0.47
    feitura
    -0.47
    Dział
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
    WebElementEntity
    0.72
    protoc
    0.69
    Revenir
    0.67
     дописавши
    0.64
    migrationBuilder
    0.64
    jspx
    0.62
    PRNewswire
    0.60
    rawDesc
    0.60
     casserole
    0.59
    Activations Density 0.180%

    No Known Activations