© 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. 41-GEMMASCOPE-RES-16K
    11. 8483
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables within scientific or technical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Katrina
    -0.76
    Katrina
    -0.68
     Paulson
    -0.64
     Jasmin
    -0.60
     Aroma
    -0.57
     Lauder
    -0.57
    Aroma
    -0.57
     Geraldine
    -0.57
     Colman
    -0.57
     Melton
    -0.56
    POSITIVE LOGITS
     bunny
    0.79
     Rabbit
    0.78
     Lara
    0.77
     rabbit
    0.77
     Bunny
    0.75
     Alice
    0.75
     rabbits
    0.73
    Rabbit
    0.72
    Lara
    0.71
    Bunny
    0.70
    Activations Density 1.626%

    No Known Activations