© 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. 11-GEMMASCOPE-RES-16K
    11. 2806
    Prev
    Next
    INDEX
    Explanations

    content related to judicial rulings and constitutional challenges

    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
     FetchType
    -0.89
     noqa
    -0.87
    PYX
    -0.79
    abestanden
    -0.73
    tagHelperRunner
    -0.71
     Pentecost
    -0.70
    ंदीखरीदारी
    -0.69
     propOrder
    -0.69
    esModule
    -0.69
    ScopeManager
    -0.69
    POSITIVE LOGITS
     lawsuits
    0.56
     lawsuit
    0.52
     court
    0.51
     legal
    0.51
     Supreme
    0.50
     hukum
    0.48
     Court
    0.47
    titutional
    0.46
    databind
    0.44
    Supreme
    0.44
    Activations Density 0.727%

    No Known Activations