© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13492
    Prev
    Next
    INDEX
    Explanations

    elements related to gene and transcription regulation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.76
     bezeichneter
    -0.75
    AsUp
    -0.72
    AccessorTable
    -0.60
     propOrder
    -0.56
    RTEE
    -0.53
    thermal
    -0.52
    aarrggbb
    -0.51
    expandindo
    -0.51
    oxyd
    -0.50
    POSITIVE LOGITS
     Segment
    0.71
    segment
    0.69
    ATA
    0.68
     vastaan
    0.65
     Fuels
    0.65
     segment
    0.65
    postMessage
    0.63
     kasarigan
    0.62
    Segment
    0.62
     segments
    0.62
    Activations Density 0.080%

    No Known Activations