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

    Neuronpedia

    Jacobian LensNEW
    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. 5924
    Prev
    Next
    INDEX
    Explanations

    references to federal laws and regulations

    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
     للاسماء
    -0.77
     ParseException
    -0.76
     Gust
    -0.74
     calli
    -0.74
     Ips
    -0.72
    stums
    -0.71
     Kost
    -0.71
     LoggerFactory
    -0.69
    sstream
    -0.67
    soort
    -0.66
    POSITIVE LOGITS
     Federal
    1.32
     federal
    1.23
     FEDERAL
    1.09
    Federal
    1.08
    federal
    1.00
    Feder
    0.97
     fédéral
    0.95
     government
    0.94
     Feder
    0.93
     federally
    0.93
    Activations Density 0.092%

    No Known Activations