© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    phrases related to biochemical processes and gene regulation

    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
    RegistryLite
    -0.50
    UrlResolution
    -0.49
     allá
    -0.43
    desliz
    -0.43
    mapStateToProps
    -0.43
    Насе
    -0.43
     célè
    -0.42
     témoignage
    -0.42
     PopupWindow
    -0.42
    Linki
    -0.41
    POSITIVE LOGITS
     surla
    0.60
     absent
    0.48
     present
    0.48
    RenderAtEndOf
    0.47
    
    0.46
     insensitive
    0.45
     sensitive
    0.44
     associated
    0.43
    OCCURRED
    0.42
     fieldNum
    0.41
    Activations Density 1.313%

    No Known Activations