© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15268
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to urinary incontinence and its classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.41
    fromnode
    -0.41
    postIndex
    -0.40
     BrowserModule
    -0.40
     shut
    -0.39
     فريبيس
    -0.38
     deſt
    -0.38
    WebServlet
    -0.38
    GeneratedCode
    -0.38
    demment
    -0.37
    POSITIVE LOGITS
     urine
    0.78
     urinary
    0.77
     Urine
    0.69
     Urinary
    0.68
    Urine
    0.68
     orina
    0.68
     bladder
    0.61
     ureter
    0.58
     Urin
    0.56
    Uro
    0.56
    Activations Density 0.453%

    No Known Activations