© 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. 11-GEMMASCOPE-RES-16K
    11. 12822
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associations with data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.77
    Hentet
    -0.76
    hyrchwyd
    -0.75
    UIControlState
    -0.74
    hoeddwyd
    -0.72
    culin
    -0.71
    Geplaatst
    -0.71
    Источник
    -0.71
    CppMethod
    -0.71
    adaptiveStyles
    -0.70
    POSITIVE LOGITS
     GP
    0.52
     Heritage
    0.45
     inget
    0.41
    main
    0.40
    Heritage
    0.39
     astore
    0.39
     Rache
    0.38
    inière
    0.37
     |
    0.37
    InfoList
    0.37
    Activations Density 0.151%

    No Known Activations