© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    references to the Tru mai language and its speakers, particularly in the context of cultural and anthropological studies

    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
    LayoutPanel
    -0.60
     disambiguazione
    -0.59
    Diweddarwch
    -0.55
    ometra
    -0.51
    poche
    -0.50
    bootstrapcdn
    -0.48
    mainwindow
    -0.48
    requ
    -0.46
     الحره
    -0.46
    jetunion
    -0.45
    POSITIVE LOGITS
     themselves
    0.69
    themselves
    0.63
    IMPORTED
    0.62
    selves
    0.62
     popolo
    0.61
    Hentet
    0.59
    KommentareTeilen
    0.58
    uestamente
    0.57
    felves
    0.56
    новништво
    0.55
    Activations Density 0.434%

    No Known Activations