© 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. 13726
    Prev
    Next
    INDEX
    Explanations

    ingredients and vegetables commonly used in cooking recipes

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

    onions and other vegetables

    np_acts-logits-general · gemini-2.0-flash

    onion and vegetables

    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
     ब्रेकडाउन
    -0.63
    relativeTime
    -0.54
     autorytatywna
    -0.49
    硃
    -0.45
    AnchorStyles
    -0.45
     мәкал
    -0.45
     '\\;'
    -0.44
     disambiguazione
    -0.44
    TemporalType
    -0.43
    :✨
    -0.43
    POSITIVE LOGITS
     onion
    0.81
     vegetable
    0.81
     vegetables
    0.80
    Vegetable
    0.76
     Vegetable
    0.75
     veggies
    0.75
     potato
    0.75
     Vegetables
    0.73
     onions
    0.72
     carrot
    0.72
    Activations Density 0.179%

    No Known Activations