© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3637
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to package and import statements in coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     org
    -0.82
     MainAxisSize
    -0.82
     HttpNotFound
    -0.79
    transQ
    -0.77
    makeConstraints
    -0.77
    nologue
    -0.75
    awtextra
    -0.75
    adaptiveStyles
    -0.74
    RTSC
    -0.74
    inSlope
    -0.74
    POSITIVE LOGITS
    import
    0.47
    order
    0.46
    .
    0.44
    ga
    0.43
    ://
    0.41
     order
    0.41
     
    0.41
    ge
    0.40
      
    0.40
    group
    0.39
    Activations Density 0.067%

    No Known Activations