© 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. 116738
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons for current situations or personal experiences

    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
     Houſe
    -0.51
     Anſ
    -0.50
     Jefus
    -0.45
     houſe
    -0.44
     descomp
    -0.43
     faſt
    -0.43
     instin
    -0.43
     Majefty
    -0.41
     Chriftian
    -0.41
     jeito
    -0.40
    POSITIVE LOGITS
    bkz
    0.68
     ویکی‌پدی
    0.65
     אשר
    0.65
     Chwiliwch
    0.64
     okuyayım
    0.63
     forthwith
    0.62
    Hentet
    0.58
     presso
    0.57
     attempted
    0.57
     resourceCulture
    0.57
    Activations Density 0.320%

    No Known Activations