© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6307
    Prev
    Next
    INDEX
    Explanations

    references to leadership roles or titles, particularly related to "chairman" and "chair."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     all
    -0.62
     so
    -0.61
     most
    -0.58
     number
    -0.57
     
    -0.57
    ecu
    -0.55
     ung
    -0.54
    ool
    -0.54
     nal
    -0.53
    TRAVIS
    -0.53
    POSITIVE LOGITS
     chairmen
    1.73
     CHAIRMAN
    1.61
     chairs
    1.54
     CHAIR
    1.50
     chairman
    1.50
     Chairs
    1.48
     Chairman
    1.45
     chair
    1.45
     Chair
    1.44
    Chairs
    1.43
    Activations Density 0.074%

    No Known Activations