Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6511
    Prev
    Next
    INDEX
    Explanations

    terms related to epilepsy and its treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Epilepsy, seizures, or anticonvulsant treatments

    np_acts-logits-general · gemini-2.0-flash

    epilepsy and seizures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    TagMode
    -0.66
     שוליים
    -0.59
     ویکی‌پدیا
    -0.54
    CppMethod
    -0.51
     Exactos
    -0.51
    AccessorTable
    -0.50
     autorytatywna
    -0.49
     oprot
    -0.49
     wikipagina
    -0.48
     contextLoads
    -0.47
    POSITIVE LOGITS
     epilepsy
    0.87
     Epilepsy
    0.84
     epileptic
    0.67
     seizures
    0.66
     seizure
    0.66
     Epile
    0.66
     Seiz
    0.62
     Seizures
    0.62
     epile
    0.61
     conv
    0.51
    Activations Density 0.444%

    No Known Activations