© 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. 9-GEMMASCOPE-RES-131K
    11. 93936
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface elements and positive action buttons

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

    protéase inhibitors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -0.83
     imagui
    -0.79
    SequentialGroup
    -0.78
    ſſung
    -0.78
     oprot
    -0.76
    ſicht
    -0.76
    Personensuche
    -0.75
     témoig
    -0.74
    ſehen
    -0.73
    niſſe
    -0.73
    POSITIVE LOGITS
     הס
    0.77
     הב
    0.74
     הח
    0.74
     הד
    0.69
     הש
    0.69
     הפ
    0.69
     הק
    0.67
     הע
    0.66
     הא
    0.65
     המ
    0.63
    Activations Density 0.001%

    No Known Activations