© 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. 9-GEMMASCOPE-RES-16K
    11. 5832
    Prev
    Next
    INDEX
    Explanations

    references to the Philippines and its people, particularly Filipinos

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     BoxFit
    -0.46
    InvalidProtocol
    -0.43
    ViewImports
    -0.40
    verifyException
    -0.37
    nė
    -0.35
    RegressionTest
    -0.34
    阅读原文
    -0.33
     CanadaChoose
    -0.33
     przy
    -0.33
     ves
    -0.33
    POSITIVE LOGITS
     Philippines
    1.00
     Filipino
    0.93
     Philippine
    0.92
    Philippines
    0.90
     Manila
    0.88
    Philippine
    0.86
     Filipinos
    0.82
     philippines
    0.80
    Manila
    0.77
    quiao
    0.74
    Activations Density 0.887%

    No Known Activations