© 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. 37-GEMMASCOPE-RES-16K
    11. 1798
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their related risks and complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.53
     BrowserModule
    -0.52
    UserScript
    -0.49
    Спољашње
    -0.49
     jScrollPane
    -0.47
    tangentMode
    -0.47
     дописавши
    -0.46
     okuyayım
    -0.46
     الرياضيه
    -0.46
    gnore
    -0.45
    POSITIVE LOGITS
     asthma
    1.41
     diabetes
    1.37
     arthritis
    1.33
     Alzheimer
    1.30
     Parkinson
    1.27
     cancer
    1.23
     Diabetes
    1.23
     epilepsy
    1.22
     rheumatoid
    1.19
     schizophrenia
    1.17
    Activations Density 2.281%

    No Known Activations