© 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. 35-GEMMASCOPE-RES-16K
    11. 10891
    Prev
    Next
    INDEX
    Explanations

    phrases relating to legal actions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    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
    -0.65
     okuyayım
    -0.63
    лтемелер
    -0.57
    RTLR
    -0.57
     kaarangay
    -0.55
    ViewFeatures
    -0.55
    richTextPanel
    -0.55
    անում
    -0.55
    principalTable
    -0.54
    LLocation
    -0.52
    POSITIVE LOGITS
     has
    2.09
     telah
    1.79
     have
    1.48
     đã
    1.48
     heeft
    1.10
    has
    1.09
     έχει
    1.09
     hasn
    1.02
     haberse
    0.98
    已经
    0.98
    Activations Density 3.358%

    No Known Activations