© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116704
    Prev
    Next
    INDEX
    Explanations

    references to Afghanistan and its associated entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Afghanistan and related places

    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
    Negative Logits
    rungsseite
    -0.96
     '\\;'
    -0.86
     resourceCulture
    -0.77
     AssemblyCulture
    -0.68
    findpost
    -0.66
     الحره
    -0.64
    DockStyle
    -0.63
     <=",
    -0.63
    exitRule
    -0.63
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
     Afghanistan
    1.15
     Afghan
    1.04
    Afghanistan
    1.01
     Afghans
    0.94
     Afgan
    0.91
    Afghan
    0.88
    ABUL
    0.83
     afghan
    0.75
     Kabul
    0.70
     Taliban
    0.57
    Activations Density 0.003%

    No Known Activations