© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15759
    Prev
    Next
    INDEX
    Explanations

    historical references to tribes and territorial conflicts

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

    peoples, tribes, or groups of people

    np_acts-logits-general · gemini-2.0-flash

    ethnic groups and peoples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     pertinentes
    -0.39
     callable
    -0.36
     einsch
    -0.33
    Ụ
    -0.33
     officio
    -0.33
     bedside
    -0.33
     drawer
    -0.32
    挽
    -0.32
     format
    -0.32
     weigh
    -0.32
    POSITIVE LOGITS
    MigrationBuilder
    0.88
     settlements
    0.75
     migrations
    0.74
     colonization
    0.74
     inhabiting
    0.73
     colonized
    0.72
    AddTagHelper
    0.72
     civilization
    0.70
     tribes
    0.69
     emigration
    0.68
    Activations Density 0.688%

    No Known Activations