© 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. 20-GEMMASCOPE-RES-16K
    11. 6897
    Prev
    Next
    INDEX
    Explanations

    references to Russia and Soviet-related entities, particularly in historical contexts

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

    references to Russia, Soviet Union, and Eastern European countries and historical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withIdentifier
    -0.50
     surla
    -0.50
     rhestr
    -0.49
     Welsh
    -0.47
    inguishing
    -0.46
    Welsh
    -0.44
     fos
    -0.44
    Caste
    -0.43
     Sacrifice
    -0.42
     kanton
    -0.42
    POSITIVE LOGITS
     Russia
    0.85
     Russian
    0.83
     Russians
    0.77
     Ivanov
    0.75
    Russia
    0.72
     Moscow
    0.72
    Russian
    0.71
     Moscú
    0.70
     Russie
    0.68
     Rusia
    0.68
    Activations Density 0.246%

    No Known Activations