© 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. 105514
    Prev
    Next
    INDEX
    Explanations

    instances of the word "package" and related comments in code or documentation

    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
    (
    -0.43
     (
    -0.35
    ↵
    -0.28
    -(
    -0.28
    -
    -0.27
     éstas
    -0.26
    éndole
    -0.25
    <bos>
    -0.23
     enfin
    -0.22
     ustedes
    -0.22
    POSITIVE LOGITS
    package
    1.83
    /*
    1.12
     AssemblyTitle
    1.05
    /**
    1.00
     package
    1.00
    #
    1.00
     Package
    0.94
     PACKAGE
    0.92
    ValueStyle
    0.92
    Geplaatst
    0.91
    Activations Density 0.005%

    No Known Activations