© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12795
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.85
     bileklik
    -0.81
     eşofman
    -0.79
     küpe
    -0.79
     taşlı
    -0.74
     kağıdı
    -0.74
     hırka
    -0.72
     ayakkab
    -0.70
     elbise
    -0.68
     kumaş
    -0.68
    POSITIVE LOGITS
     Turkish
    1.13
     Turkey
    1.08
    Turkish
    1.01
    Turkey
    1.01
     Istanbul
    0.99
     turkish
    0.96
     Erdogan
    0.94
     turkey
    0.86
    Istanbul
    0.86
     Ankara
    0.86
    Activations Density 0.056%

    No Known Activations