© 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. 105364
    Prev
    Next
    INDEX
    Explanations

    occurrences of variables and session data in PHP code

    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
     estekak
    -0.63
    AnimationsModule
    -0.61
     않
    -0.57
     Girard
    -0.57
     متعلقه
    -0.56
     austin
    -0.54
    //}
    -0.54
    kegaard
    -0.53
    DMC
    -0.52
    UnusedPrivate
    -0.52
    POSITIVE LOGITS
    ($_
    1.13
     $_
    1.12
     ($_
    1.05
    ,$_
    1.04
    =$_
    0.92
    .$_
    0.86
    )$_
    0.86
    $_
    0.84
    ".$_
    0.79
    ::$_
    0.67
    Activations Density 0.007%

    No Known Activations