© 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. 35-GEMMASCOPE-RES-16K
    11. 7331
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical events and historical context related to the Soviet Union

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.74
    脚注の使い方
    -0.69
     препратки
    -0.65
    ніципалі
    -0.64
    ">//
    -0.63
     defaultstate
    -0.61
     autorytatywna
    -0.58
    出版年
    -0.57
     ujednoznacz
    -0.57
     صوتيه
    -0.55
    POSITIVE LOGITS
     Soviet
    1.30
     soviet
    1.02
     communist
    1.00
    Soviet
    0.99
     Soviets
    0.96
     Communist
    0.93
     USSR
    0.91
     sovi
    0.91
     Stalin
    0.90
     socialist
    0.83
    Activations Density 0.294%

    No Known Activations