© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 38250
    Prev
    Next
    INDEX
    Explanations

    terms and attributes related to UI components and interactions in a web development context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    fa fa-circle-o 'selected' hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    #+#
    -0.44
    getSystemService
    -0.39
     mill
    -0.36
     FAT
    -0.36
     dro
    -0.35
     Mess
    -0.34
     scon
    -0.33
     Sec
    -0.33
     mess
    -0.32
     Fate
    -0.32
    POSITIVE LOGITS
     bluzka
    0.74
    adaptiveStyles
    0.61
     koszulka
    0.59
     noastră
    0.57
    IUrlHelper
    0.56
     appunto
    0.56
    parsedMessage
    0.55
     Biôgrafia
    0.54
    <?
    0.54
     święta
    0.54
    Activations Density 0.057%

    No Known Activations