© 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. 104787
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions surrounding logic and reasoning

    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
    __(/*!
    -0.41
    SupportActionBar
    -0.30
     marcado
    -0.30
    ⓘ
    -0.29
     précieux
    -0.29
     Mangel
    -0.29
     marqué
    -0.28
     TestBed
    -0.28
     markedly
    -0.28
     Jewell
    -0.27
    POSITIVE LOGITS
     logically
    0.76
     illogical
    0.75
     reasoned
    0.74
     logic
    0.73
     logique
    0.72
     logical
    0.72
     Logical
    0.69
    Reasonable
    0.69
    省市镇
    0.69
     reasoning
    0.68
    Activations Density 0.034%

    No Known Activations