© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14879
    Prev
    Next
    INDEX
    Explanations

    geographic references, particularly related to Turkey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Turkey (or Turkish)

    np_acts-logits-general · gemini-2.0-flash

    Turkey and turkish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     küpe
    -0.83
     bileklik
    -0.76
     elbise
    -0.72
     kılıf
    -0.71
     kağıdı
    -0.70
     taşlı
    -0.69
     Namib
    -0.69
     çantası
    -0.67
    Omaha
    -0.66
     kumaş
    -0.65
    POSITIVE LOGITS
     Turkish
    1.99
     Turkey
    1.98
    Turkey
    1.82
    Turkish
    1.76
     Istanbul
    1.61
     turkish
    1.53
     turkey
    1.48
    Istanbul
    1.46
    turkey
    1.46
     Turquía
    1.44
    Activations Density 0.090%

    No Known Activations