© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33535
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals in a professional context

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

    Nigeria

    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
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.45
     references
    -0.40
     enhancements
    -0.34
    مراجع
    -0.33
     coffees
    -0.33
     honors
    -0.33
    ⚾
    -0.33
    MenuInflater
    -0.32
     einge
    -0.32
     Yukon
    -0.31
    POSITIVE LOGITS
     Nigeria
    0.86
    Nigeria
    0.78
     Nigerian
    0.78
    Nigerian
    0.77
     Nigerians
    0.75
     NIGERIA
    0.71
    ₦
    0.69
     Lagos
    0.66
     niger
    0.66
    Lagos
    0.65
    Activations Density 0.063%

    No Known Activations