© 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. 15-GEMMASCOPE-RES-16K
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    mentions of investigations and reports, particularly in a governmental or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.68
    SaveChangesAsync
    -0.67
    ंदीखरीदारी
    -0.63
     useDispatch
    -0.62
    PhysRevLett
    -0.59
     plagioclase
    -0.58
     useState
    -0.58
     registrations
    -0.56
     Apprentice
    -0.55
     actualité
    -0.55
    POSITIVE LOGITS
     report
    1.18
     Report
    0.94
    report
    0.88
     reports
    0.84
    Report
    0.82
     conclusions
    0.82
     analysis
    0.81
    报告
    0.76
     rapor
    0.75
     REPORT
    0.75
    Activations Density 0.541%

    No Known Activations