© 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. 31-GEMMASCOPE-RES-131K
    11. 61297
    Prev
    Next
    INDEX
    Explanations

    references to specific ethnicities or cultural identities

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

    languages and ethnicities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     laikā
    -0.47
    ed
    -0.43
    openConnection
    -0.40
    er
    -0.36
    者
    -0.34
     života
    -0.33
     galima
    -0.32
     místě
    -0.32
     expectativa
    -0.32
     interesa
    -0.32
    POSITIVE LOGITS
    ########.
    0.81
     Nadu
    0.81
     Tamil
    0.72
    Tamil
    0.68
     OnInit
    0.62
    /*
    0.60
    tamil
    0.59
    󠁮
    0.58
    reportWebVitals
    0.55
    ✭✭
    0.54
    Activations Density 0.002%

    No Known Activations