© 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. 41-GEMMASCOPE-RES-16K
    11. 13699
    Prev
    Next
    INDEX
    Explanations

    terms related to viral DNA and RNA in scientific studies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.61
    
    -0.59
     malah
    -0.57
     addirittura
    -0.57
     justru
    -0.56
     propOrder
    -0.56
     zelfs
    -0.55
    !—
    -0.54
     persino
    -0.51
     talvez
    -0.51
    POSITIVE LOGITS
     using
    0.74
     employing
    0.67
     separately
    0.60
     applying
    0.56
     utilizing
    0.55
     according
    0.54
     yielding
    0.54
     covering
    0.53
     adopting
    0.53
     aiming
    0.52
    Activations Density 3.300%

    No Known Activations