© 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. 5-GEMMASCOPE-RES-16K
    6. 3350
    Prev
    Next
    INDEX
    Explanations

    references to "main" or significant components in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彿
    -0.72
     Tribe
    -0.71
     phénom
    -0.71
     Fleck
    -0.70
    Oise
    -0.70
    tinyos
    -0.70
     pédagog
    -0.68
     polvere
    -0.68
     pédagogique
    -0.67
     Réponses
    -0.67
    POSITIVE LOGITS
     Main
    2.13
     main
    2.04
    Main
    1.97
     MAIN
    1.95
    MAIN
    1.84
    main
    1.70
    getMain
    1.41
     mains
    1.37
     Mains
    1.31
     Haupt
    1.31
    Activations Density 0.039%

    No Known Activations