© 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. 104778
    Prev
    Next
    INDEX
    Explanations

    high-frequency or important terms in a discussion or text, particularly related to concerns about infection and healthcare

    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
     betweenstory
    -0.81
     defaultstate
    -0.80
    httphttps
    -0.78
    AddTagHelper
    -0.77
    IsContent
    -0.77
    ⟬
    -0.76
    ScopeManager
    -0.76
    GEBURTSDATUM
    -0.75
     Administrativna
    -0.73
    twimg
    -0.72
    POSITIVE LOGITS
    便
    0.33
    Common
    0.33
    vänt
    0.31
    ற்ப
    0.31
    Autor
    0.30
     virke
    0.29
    ∇
    0.29
    除了
    0.28
    Ủ
    0.28
    Author
    0.27
    Activations Density 0.001%

    No Known Activations