Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1599
    Prev
    Next
    INDEX
    Explanations

    references to chocolate and related desserts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.90
    msgTypes
    -0.83
    AnchorStyles
    -0.82
    imothy
    -0.80
     consign
    -0.79
     Pacer
    -0.75
    awaiter
    -0.74
     communiquez
    -0.73
    onViewCreated
    -0.73
     समीक्षाओं
    -0.72
    POSITIVE LOGITS
     chocolate
    2.78
     Chocolate
    2.63
    chocolate
    2.58
    Chocolate
    2.56
    OCOLATE
    2.08
     chocolates
    1.83
     chocol
    1.80
     cioccolato
    1.62
    チョコレート
    1.57
     chocolat
    1.53
    Activations Density 0.038%

    No Known Activations