© 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. 20-GEMMASCOPE-RES-131K
    11. 104935
    Prev
    Next
    INDEX
    Explanations

    positive and pricing-related language in a business context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Negative Logits
    :✨
    -0.77
    ########.
    -0.72
    Tembelea
    -0.72
     незавершена
    -0.69
    RenderAtEndOf
    -0.66
     resourceCulture
    -0.60
     تضيفلها
    -0.60
     kasarigan
    -0.59
    ፩
    -0.59
     صوتيه
    -0.57
    POSITIVE LOGITS
     către
    0.35
     Volkes
    0.33
     kunci
    0.32
     inginkan
    0.32
     molecular
    0.31
    Toponymie
    0.31
     dimo
    0.31
     burbu
    0.31
     maquin
    0.30
     côtés
    0.30
    Activations Density 0.008%

    No Known Activations