© 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. 31-GEMMASCOPE-RES-16K
    11. 3219
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical entities, particularly countries in the Middle East

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

    references to the country Syria.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.40
     Paragu
    -0.35
    Jereo
    -0.35
     GenerationType
    -0.35
    奈川
    -0.34
     Rott
    -0.32
    läg
    -0.32
     Kansas
    -0.31
     Ind
    -0.31
    movq
    -0.31
    POSITIVE LOGITS
     Syrian
    1.08
     Syria
    0.94
    Syria
    0.92
     Aleppo
    0.83
     Damascus
    0.81
     Syrians
    0.80
     Siria
    0.71
     Assad
    0.70
    Assad
    0.66
     Syrie
    0.66
    Activations Density 0.055%

    No Known Activations