© 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. 22-GEMMASCOPE-RES-16K
    11. 11937
    Prev
    Next
    INDEX
    Explanations

    specific references to temporal or sequential events and their impact on outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Aufklärung
    -0.30
     efectivo
    -0.28
     escrit
    -0.28
     aprovecha
    -0.28
    đồng
    -0.27
     conquête
    -0.26
     Kerja
    -0.26
     individuelles
    -0.25
     Umum
    -0.25
     aprove
    -0.24
    POSITIVE LOGITS
     AssemblyCulture
    0.86
    URLException
    0.85
    ScopeManager
    0.84
    AndEndTag
    0.78
    RTHOOK
    0.76
     otomatig
    0.73
    AnchorStyles
    0.71
    EClass
    0.70
    verifyException
    0.69
    
    0.69
    Activations Density 1.166%

    No Known Activations