© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105285
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and historical figures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Negative Logits
     terciopelo
    -0.40
     total
    -0.39
     totales
    -0.39
    ้ย
    -0.38
     eléctricas
    -0.38
     totaal
    -0.37
     inalámb
    -0.36
     substantially
    -0.36
     Götter
    -0.36
     cuchara
    -0.35
    POSITIVE LOGITS
     jadx
    0.65
     Chwiliwch
    0.61
     estekak
    0.60
    IUrlHelper
    0.60
     nakalista
    0.59
     utafitiHapana
    0.59
     disambiguazione
    0.56
     Infórmanos
    0.55
     للمعارف
    0.55
     ModelExpression
    0.53
    Activations Density 0.036%

    No Known Activations