© 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. 9-GEMMASCOPE-RES-16K
    11. 6957
    Prev
    Next
    INDEX
    Explanations

    terms associated with epilepsy and its effects on cognition and language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.64
     autorytatywna
    -0.61
    parsedMessage
    -0.60
     contextLoads
    -0.60
    Personendaten
    -0.57
    InitVars
    -0.57
    TagMode
    -0.56
    principalTable
    -0.56
     StatefulWidget
    -0.55
     Winaray
    -0.53
    POSITIVE LOGITS
     epilepsy
    0.74
     Epilepsy
    0.69
     epileptic
    0.64
     Epile
    0.62
     seizures
    0.60
     seizure
    0.59
     epile
    0.54
     Seiz
    0.53
     Seizures
    0.52
    conv
    0.43
    Activations Density 0.376%

    No Known Activations