© 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. 3-GEMMASCOPE-RES-16K
    11. 6050
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" in various contexts, particularly where attention or observation is emphasized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.81
     ब्रेकडाउन
    -0.80
    PerformLayout
    -0.71
     otomatig
    -0.69
    libft
    -0.63
    oa̍t
    -0.63
    
    -0.62
    WebElementEntity
    -0.60
    存于互联网档案馆
    -0.60
     StatefulWidget
    -0.60
    POSITIVE LOGITS
     glance
    0.75
     stroll
    0.68
     vistazo
    0.66
     stint
    0.63
     glances
    0.62
     visit
    0.60
     visita
    0.59
     detour
    0.59
     glimpse
    0.59
     foray
    0.59
    Activations Density 0.295%

    No Known Activations