© 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. 37-GEMMASCOPE-RES-16K
    11. 5195
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions and organizations in China

    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
    ⟬
    -0.48
     ujednoznacz
    -0.40
     McKee
    -0.38
    UIImageView
    -0.36
     ganchillo
    -0.35
    UrlResolution
    -0.34
     Unger
    -0.34
     Servlet
    -0.34
     McLeod
    -0.34
    Servlet
    -0.33
    POSITIVE LOGITS
     Chinese
    2.88
     China
    2.70
    Chinese
    2.55
    China
    2.47
     chinese
    2.45
     CHINESE
    2.36
     china
    2.33
     CHINA
    2.28
     китай
    2.22
     Китай
    2.19
    Activations Density 0.482%

    No Known Activations