© 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. 19-GEMMASCOPE-RES-16K
    11. 15501
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or names within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -1.17
    ousands
    -1.16
    ousand
    -1.12
    ratulations
    -1.11
    encils
    -1.10
    arranty
    -1.04
     AssemblyCulture
    -1.04
    ineſs
    -1.03
    elfare
    -1.02
    Geplaatst
    -1.01
    POSITIVE LOGITS
    il
    0.79
    k
    0.76
    ut
    0.76
    z
    0.71
    á
    0.71
    é
    0.68
    us
    0.68
    ys
    0.68
    el
    0.66
    ig
    0.65
    Activations Density 0.775%

    No Known Activations