© 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. 34-GEMMASCOPE-RES-16K
    11. 3258
    Prev
    Next
    INDEX
    Explanations

    key characteristics and desirability of American muscle cars

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     gynhyrchwyd
    -0.55
    
    -0.48
    Хьажоргаш
    -0.39
    htbp
    -0.39
     AssemblyTitle
    -0.36
    AccessorTable
    -0.36
     Meksiku
    -0.34
     esternos
    -0.34
    
    -0.32
    Erstellt
    -0.31
    POSITIVE LOGITS
     collectors
    1.99
     collector
    1.93
     coleccion
    1.73
     Collectors
    1.66
     collectible
    1.66
     collectibles
    1.59
     collection
    1.58
     collecting
    1.55
    collector
    1.54
     collections
    1.53
    Activations Density 0.281%

    No Known Activations