© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 4951
    Prev
    Next
    INDEX
    Explanations

    references to insurance companies and related legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.58
    TintMode
    -0.43
    coltà
    -0.43
    reportWebVitals
    -0.43
    /**
    -0.41
    writeFieldEnd
    -0.40
    󠁴
    -0.40
    IntoConstraints
    -0.39
    (!__
    -0.38
    RTLR
    -0.35
    POSITIVE LOGITS
     company
    3.55
    company
    2.97
     Company
    2.91
    Company
    2.78
     companies
    2.73
     COMPANY
    2.69
    公司
    2.50
    COMPANY
    2.48
     compañía
    2.44
     Companies
    2.30
    Activations Density 0.584%

    No Known Activations