© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16080
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical conflicts and territorial disputes

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

    Territorial disputes and occupation

    np_acts-logits-general · gemini-2.0-flash

    territorial claims and occupation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     للاسماء
    -0.65
    lateur
    -0.57
     Roskov
    -0.54
     становника
    -0.54
     Hendrick
    -0.52
     memu
    -0.51
    Activator
    -0.50
    Inggris
    -0.49
    EMBLY
    -0.49
    CESO
    -0.48
    POSITIVE LOGITS
     disputed
    0.97
     territory
    0.97
     territories
    0.93
     contested
    0.93
     occupied
    0.89
     Occupied
    0.81
    occupied
    0.80
     claimed
    0.80
     territorial
    0.78
     seized
    0.75
    Activations Density 0.301%

    No Known Activations