© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9411
    Prev
    Next
    INDEX
    Explanations

    lines of code that include header files or import statements in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     InputDecoration
    -0.98
    LookAnd
    -0.94
     oprot
    -0.91
    Autoritní
    -0.89
     OMITBAD
    -0.85
    DockStyle
    -0.84
     autorytatywna
    -0.83
    complexContent
    -0.82
    EndGlobalSection
    -0.81
    AsUp
    -0.81
    POSITIVE LOGITS
    ↵↵
    0.75
    <eos>
    0.66
    ↵↵↵
    0.54
     The
    0.53
    </tr>
    0.53
      
    0.50
    ↵
    0.50
     also
    0.48
    .
    0.47
    려
    0.46
    Activations Density 0.061%

    No Known Activations