© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 9901
    Prev
    Next
    INDEX
    Explanations

    references to previous points or statements made in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentioned earlier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vechi
    -0.56
     vecchia
    -0.52
     legacy
    -0.50
     viejos
    -0.50
     Subsequent
    -0.50
     viejo
    -0.50
     actuels
    -0.50
     Vergangenheit
    -0.49
     vieux
    -0.49
     vieille
    -0.48
    POSITIVE LOGITS
     earlier
    1.33
     previously
    1.09
    Earlier
    1.02
    earlier
    1.02
     Earlier
    1.02
     Previously
    0.91
     ранее
    0.90
     wcześniej
    0.89
    Previously
    0.89
    previously
    0.87
    Activations Density 0.131%

    No Known Activations