© 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. 15430
    Prev
    Next
    INDEX
    Explanations

    names of medical institutions and hospitals in South Korea

    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
    ChildScrollView
    -0.61
     disambiguazione
    -0.56
    الحياه
    -0.54
     ब्रेकडाउन
    -0.52
     свер
    -0.46
     lenker
    -0.43
    velocityY
    -0.41
     NgModule
    -0.38
     Wiktionnaire
    -0.37
    Попис
    -0.37
    POSITIVE LOGITS
     Korea
    1.39
     Korean
    1.37
     Seoul
    1.22
     Koreans
    1.20
    Korea
    1.16
    Korean
    1.13
     korean
    1.11
     korea
    1.08
     Corée
    1.07
     coreano
    1.02
    Activations Density 0.463%

    No Known Activations