© 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. 105300
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental contamination and remediation efforts

    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
     net
    -0.35
     AssemblyCulture
    -0.35
     createState
    -0.35
     Gew
    -0.33
     fä
    -0.33
    yntaxException
    -0.33
    CodeAttribute
    -0.33
     Net
    -0.32
     ciri
    -0.32
    ud
    -0.31
    POSITIVE LOGITS
    SequentialGroup
    0.76
     Infórmanos
    0.66
     cleanup
    0.65
    RegressionTest
    0.63
     disambiguazione
    0.63
     remediation
    0.63
     itſelf
    0.62
     ſche
    0.60
     ſch
    0.58
     indígen
    0.57
    Activations Density 0.011%

    No Known Activations