© 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. 15308
    Prev
    Next
    INDEX
    Explanations

    mentions of significant places or events in Turkey

    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
     kılıf
    -0.66
     küpe
    -0.63
    oa̍t
    -0.60
     mümkün
    -0.57
     kalın
    -0.55
     geçir
    -0.55
     kumaş
    -0.54
     palvel
    -0.52
     baskılı
    -0.52
     çantası
    -0.52
    POSITIVE LOGITS
     Turkish
    1.35
     Turkey
    1.25
    Turkish
    1.21
     Istanbul
    1.18
    Turkey
    1.15
     Ankara
    1.12
     turkish
    1.08
     Turquía
    1.02
     turkey
    1.02
    Istanbul
    1.02
    Activations Density 0.083%

    No Known Activations