© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3766
    Prev
    Next
    INDEX
    Explanations

    mentions of ingredients and materials used in recipes or production processes

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

    "ingredients" or "materials"

    np_acts-logits-general · gemini-2.0-flash

    ingredients and materials

    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
    Искәрмәләр
    -0.69
    ViewInit
    -0.56
    SourceChecksum
    -0.51
    adaptiveStyles
    -0.51
    ьаж
    -0.51
     ModelExpression
    -0.50
    دانشنامهٔ
    -0.48
    ToScroll
    -0.46
     PrintWriter
    -0.46
    Parcelize
    -0.46
    POSITIVE LOGITS
     ingredients
    0.94
     materials
    0.78
     Ingredients
    0.76
    ingredients
    0.76
     ingredient
    0.76
     Ingredient
    0.71
     ingredi
    0.70
     ingrédients
    0.66
    Ingredients
    0.66
     ingredientes
    0.65
    Activations Density 0.458%

    No Known Activations