© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104634
    Prev
    Next
    INDEX
    Explanations

    references to various types of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     coroa
    -0.56
    miter
    -0.51
     borboleta
    -0.51
     Deane
    -0.50
    퀀
    -0.50
     Meyers
    -0.50
    ตน
    -0.48
     Gilbert
    -0.47
    뀜
    -0.47
     ritratto
    -0.47
    POSITIVE LOGITS
    Food
    1.05
     FOOD
    1.03
     Food
    1.03
    FOOD
    1.01
     food
    0.93
    food
    0.89
     Foods
    0.78
    Foods
    0.75
     Makanan
    0.73
     foods
    0.71
    Activations Density 0.015%

    No Known Activations