© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-GEMMASCOPE-RES-16K
    11. 15005
    Prev
    Next
    INDEX
    Explanations

    phrases related to clinical medical studies and patient assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.30
    헌
    -0.28
     patient
    -0.28
     Saunders
    -0.27
     s
    -0.26
     בן
    -0.26
     n
    -0.26
     V
    -0.26
     condition
    -0.25
     clinically
    -0.25
    POSITIVE LOGITS
    RegressionTest
    0.88
    AndEndTag
    0.85
    expandindo
    0.84
     oprot
    0.84
    GOTREF
    0.83
     שוליים
    0.82
    tagHelperRunner
    0.80
     queſta
    0.80
    DockStyle
    0.79
    sizeCache
    0.77
    Activations Density 6.481%

    No Known Activations