© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8673
    Prev
    Next
    INDEX
    Explanations

    specific sports teams, players, and game-related statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     Under
    -0.38
     polaire
    -0.34
     fisuras
    -0.34
     cadeia
    -0.33
    Under
    -0.33
     Sede
    -0.33
     UNDER
    -0.33
     marbre
    -0.33
     expertise
    -0.32
     curé
    -0.32
    POSITIVE LOGITS
     utafitiHapana
    0.82
     صوتيه
    0.62
    UnusedPrivate
    0.57
     gynhyrchwyd
    0.56
     المعيارى
    0.55
     rivals
    0.54
    EndContext
    0.54
     مرئيه
    0.54
    tanleria
    0.53
     ویکی‌پدیا
    0.52
    Activations Density 0.497%

    No Known Activations