© 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. 128762
    Prev
    Next
    INDEX
    Explanations

    negative phrases or symbols associated with loss or disappointment

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

    YYYY-YY year ranges

    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
    msgTypes
    -0.73
     Italijani
    -0.71
    contentLoaded
    -0.69
     שוליים
    -0.69
    хьтан
    -0.65
     Италијани
    -0.61
    ðsíða
    -0.60
     nonUne
    -0.60
     mergeFrom
    -0.60
    ⤹
    -0.59
    POSITIVE LOGITS
     winter
    0.62
     season
    0.52
     Winter
    0.50
    winter
    0.50
     autumn
    0.46
     winters
    0.46
     offseason
    0.46
    Winter
    0.46
     year
    0.41
    hiver
    0.40
    Activations Density 0.011%

    No Known Activations