© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 9396
    Prev
    Next
    INDEX
    Explanations

    topics related to educational initiatives and curriculum improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.82
     larmes
    -0.77
     vœux
    -0.76
     bienfaits
    -0.73
     lèvres
    -0.73
     âmes
    -0.67
     prêtres
    -0.66
     vérit
    -0.65
     dieux
    -0.65
     rigue
    -0.64
    POSITIVE LOGITS
     setups
    1.32
     frameworks
    1.31
     regimes
    1.27
     programmes
    1.26
     schemes
    1.25
     situations
    1.24
     programs
    1.23
     environments
    1.23
     regimens
    1.20
     organizations
    1.17
    Activations Density 5.042%

    No Known Activations