© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38331
    Prev
    Next
    INDEX
    Explanations

    terms related to seizures and their effects

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

    medical episodes and fits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.57
     Савезне
    -0.49
     peuples
    -0.47
    ]")]
    -0.47
     transparan
    -0.45
    AnchorStyles
    -0.44
    wertig
    -0.43
    hadiran
    -0.42
    胧
    -0.42
     intérêts
    -0.41
    POSITIVE LOGITS
     convulsions
    0.60
    printStackTrace
    0.59
     outburst
    0.55
     spasms
    0.55
     eruption
    0.54
     attack
    0.53
     outbursts
    0.53
     occurring
    0.52
     occur
    0.51
     spasm
    0.51
    Activations Density 0.052%

    No Known Activations