© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1410
    Prev
    Next
    INDEX
    Explanations

    themes of darkness, grief, and emotional struggles within artistic expressions

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

    dark, bleak, and negative emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     kasarigan
    -0.62
     للاسماء
    -0.61
    LabelTagHelper
    -0.61
     Numerade
    -0.60
    verwijspagina
    -0.59
    migrationBuilder
    -0.57
    MessageTagHelper
    -0.54
     otomatig
    -0.54
    WireFormatLite
    -0.52
    postIndex
    -0.52
    POSITIVE LOGITS
     dark
    0.91
     somber
    0.88
     gloomy
    0.88
     darker
    0.81
     gloom
    0.77
     bleak
    0.77
     pessimistic
    0.76
     pessimism
    0.73
     sombre
    0.73
     negative
    0.73
    Activations Density 0.113%

    No Known Activations