© 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 - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10522
    Prev
    Next
    INDEX
    Explanations

    references to significant events or milestones in narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    addCriterion
    -0.60
    featureID
    -0.56
    XmlAccessorType
    -0.55
    principalColumn
    -0.55
    BeginInit
    -0.55
    WriteLiteral
    -0.48
     antemano
    -0.47
    tagHelperRunner
    -0.47
    ValueStyle
    -0.43
     ocupación
    -0.42
    POSITIVE LOGITS
     ());
    0.52
    InBytes
    0.51
      
    0.49
    Ранее
    0.48
    Jura
    0.48
    literal
    0.47
    iální
    0.47
     👆
    0.47
     vgl
    0.46
     ///
    0.46
    Activations Density 1.124%

    No Known Activations