© 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. 36-GEMMASCOPE-RES-16K
    11. 8061
    Prev
    Next
    INDEX
    Explanations

    specific terms related to examination and treatment mechanisms in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.56
     bambú
    -0.50
     increí
    -0.50
     Infór
    -0.48
     Perſ
    -0.48
     ſch
    -0.47
     Reſ
    -0.47
     ſeveral
    -0.47
     EconPapers
    -0.46
    tonsoft
    -0.46
    POSITIVE LOGITS
     body
    1.10
     shell
    0.96
     base
    0.90
    body
    0.88
     bodies
    0.87
     outer
    0.87
     hull
    0.82
     BODY
    0.82
     chassis
    0.81
     shells
    0.80
    Activations Density 1.207%

    No Known Activations