© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8673
    Prev
    Next
    INDEX
    Explanations

    cooking-related terms, specifically those involving ovens and baking processes

    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
     resourceCulture
    -0.83
     tiểu
    -0.66
    andria
    -0.66
     CreateTagHelper
    -0.65
     Giacomo
    -0.64
    kommer
    -0.62
     Byrne
    -0.62
    败
    -0.62
    ondre
    -0.61
    FirstOrDefault
    -0.60
    POSITIVE LOGITS
     oven
    2.33
     Oven
    1.97
     ovens
    1.74
    Oven
    1.72
    oven
    1.58
     forno
    1.15
     horno
    1.06
     Dun
    0.95
     kiln
    0.92
     stove
    0.91
    Activations Density 0.025%

    No Known Activations