© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28312
    Prev
    Next
    INDEX
    Explanations

    emotional descriptors related to distress, inspiration, and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    intense emotions and experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.82
     للاسماء
    -0.81
     indígen
    -0.74
    RectangleBorder
    -0.72
    AddTagHelper
    -0.71
     "..\..\..\
    -0.68
    出版年
    -0.68
     Geiſt
    -0.68
    ContentLoaded
    -0.67
    tagHelperRunner
    -0.66
    POSITIVE LOGITS
     eer
    0.35
     seeing
    0.35
     if
    0.34
     uncanny
    0.33
     G
    0.32
     fact
    0.31
    TextChanged
    0.30
     eerie
    0.30
    auto
    0.29
     happened
    0.29
    Activations Density 0.023%

    No Known Activations