© 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. 33-GEMMASCOPE-RES-16K
    11. 9341
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages related to health and disease prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.40
     TType
    -0.33
    lossians
    -0.33
    ilever
    -0.29
    XtraReports
    -0.28
     Ergän
    -0.27
    rawtypes
    -0.27
    iastes
    -0.27
    reg
    -0.27
    */),
    -0.27
    POSITIVE LOGITS
     infected
    1.53
     infection
    1.41
     infect
    1.38
     contaminated
    1.32
     infecting
    1.30
    infected
    1.26
    infection
    1.23
     Infected
    1.22
     transmission
    1.21
    感染
    1.21
    Activations Density 0.688%

    No Known Activations