© 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. 36-GEMMASCOPE-RES-16K
    11. 5362
    Prev
    Next
    INDEX
    Explanations

    statistical terminology and expressions related to probability distributions

    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
     Ramsey
    -0.55
     Gaud
    -0.53
     Tutu
    -0.53
     Murdoch
    -0.52
     donut
    -0.50
     Frey
    -0.50
     McCulloch
    -0.50
     Yoongi
    -0.50
     Spenser
    -0.50
     Soko
    -0.50
    POSITIVE LOGITS
     Lozano
    0.75
     Figue
    0.65
     Alvarado
    0.64
     Valladolid
    0.61
     Pless
    0.59
     Ashby
    0.57
     Keating
    0.57
    endaft
    0.54
     McIn
    0.53
     Schweitzer
    0.53
    Activations Density 1.767%

    No Known Activations