© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 17302
    Prev
    Next
    INDEX
    Explanations

    instances of sitting or being seated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )}>
    -0.54
     Bode
    -0.52
    ERIES
    -0.50
    icali
    -0.49
    hauer
    -0.48
    endif
    -0.47
     outstanding
    -0.47
    ktory
    -0.46
    fontawesome
    -0.46
     line
    -0.46
    POSITIVE LOGITS
     seating
    1.31
     seated
    1.25
     Seating
    1.22
     seat
    1.15
     seats
    1.15
     Seats
    1.11
     chair
    1.10
     chairs
    1.09
     Seat
    1.04
    seat
    1.01
    Activations Density 0.021%

    No Known Activations