© 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. 31-GEMMASCOPE-RES-131K
    11. 2460
    Prev
    Next
    INDEX
    Explanations

    arguments and reasoning within a text

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

    stating reasons or arguments

    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
    Negative Logits
    angliski
    -0.45
    aarrggbb
    -0.44
    críbete
    -0.43
     Privacidade
    -0.42
     aprobado
    -0.38
    hadores
    -0.38
     domanda
    -0.38
    oció
    -0.36
    коменду
    -0.36
     ordinario
    -0.36
    POSITIVE LOGITS
     arguments
    1.77
     argument
    1.51
     Arguments
    1.48
     argumentos
    1.47
     reasons
    1.45
    arguments
    1.43
     аргу
    1.34
     argumento
    1.31
     argumenta
    1.30
     Argument
    1.29
    Activations Density 0.322%

    No Known Activations