© 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. 105024
    Prev
    Next
    INDEX
    Explanations

    occurrences of whitespace and structural elements in text

    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
    :✨
    -0.54
    uthorized
    -0.47
     BoxFit
    -0.47
     kaynağından
    -0.45
    AutoField
    -0.43
    🇶
    -0.43
    adaptiveStyles
    -0.42
    酒屋
    -0.42
     Wikiseite
    -0.41
    ResumeLayout
    -0.41
    POSITIVE LOGITS
    олові
    0.48
    __':
    0.46
    webElementXpaths
    0.41
    SharedCtor
    0.40
     propOrder
    0.40
    contentLoaded
    0.40
    '},
    0.39
    __":
    0.39
    KeySpec
    0.39
    期刊论文
    0.38
    Activations Density 0.042%

    No Known Activations