© 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-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4076
    Prev
    Next
    INDEX
    Explanations

    references to historical events and trauma related to the Balkans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.60
     Японии
    -0.59
    Tikang
    -0.57
     ژاپ
    -0.56
     Japon
    -0.54
     Jepang
    -0.52
     Shogun
    -0.52
    IVEREF
    -0.50
     Япо
    -0.50
     giapponese
    -0.50
    POSITIVE LOGITS
     Serbian
    1.22
     Serbia
    1.13
     Serb
    1.06
     Serbs
    1.05
     Balkan
    1.02
     Belgrade
    0.99
     Bosnia
    0.93
     Balkans
    0.93
    Serbia
    0.90
     Ser
    0.90
    Activations Density 0.514%

    No Known Activations