© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10654
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of food and desserts

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

    Desserts, especially ice cream and chocolate

    np_acts-logits-general · gemini-2.0-flash

    ice cream and chocolate desserts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Flea
    -0.50
     cebolla
    -0.50
     bawang
    -0.50
     Refugee
    -0.49
     cipolla
    -0.49
    🥗
    -0.47
    TagHelper
    -0.47
     Cabbage
    -0.47
     ensalada
    -0.47
     [*]
    -0.47
    POSITIVE LOGITS
     ice
    1.19
     chocolate
    1.05
     Chocolate
    0.97
     vanilla
    0.97
     gelato
    0.95
    chocolate
    0.95
     Ice
    0.94
    Chocolate
    0.93
     cream
    0.92
     milk
    0.89
    Activations Density 0.161%

    No Known Activations