Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2681
    Prev
    Next
    INDEX
    Explanations

    references to Russian nationality, history, and notable figures associated with Russia

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

    Russia and Russian terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     rhestr
    -0.49
     Welsh
    -0.40
    delwed
    -0.39
     fos
    -0.39
    Welsh
    -0.39
    wales
    -0.38
     Chwiliwch
    -0.36
     path
    -0.35
    λασ
    -0.35
     apariencia
    -0.34
    POSITIVE LOGITS
     Russia
    1.09
     Russian
    1.02
     Russians
    0.94
     Moscow
    0.94
    Russia
    0.92
     Russie
    0.88
     Rusia
    0.88
    Russian
    0.88
     Moscú
    0.84
     Russland
    0.84
    Activations Density 0.137%

    No Known Activations