© 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. 20-GEMMASCOPE-RES-131K
    11. 116810
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to health challenges and deficiencies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    Negative Logits
    }}$\\
    -0.41
    ')";
    -0.40
     للاسماء
    -0.40
    }{$\
    -0.40
     yake
    -0.40
    //{
    -0.40
    illaume
    -0.39
    measure
    -0.38
     Numerade
    -0.38
    '])){
    -0.38
    POSITIVE LOGITS
     begge
    0.79
     respectively
    0.78
    这两个
    0.73
     ambos
    0.70
    respectively
    0.69
     beiden
    0.68
     båda
    0.67
    どちらも
    0.67
     respectivamente
    0.65
     beide
    0.64
    Activations Density 0.429%

    No Known Activations