© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    references to clothing or items that are worn

    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
    (',')
    -0.84
     Cousins
    -0.77
    hasMoreElements
    -0.73
     Plummer
    -0.73
     decisivo
    -0.72
    Callum
    -0.70
    Slu
    -0.70
     Kristine
    -0.68
    来不及
    -0.68
    pergillus
    -0.68
    POSITIVE LOGITS
     Wear
    1.36
     wear
    1.32
    Wear
    1.24
     worn
    1.23
    wear
    1.19
     wears
    1.19
     WEAR
    1.17
     Worn
    1.09
     wore
    1.06
     Wearing
    1.02
    Activations Density 0.028%

    No Known Activations