© 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. 100878
    Prev
    Next
    INDEX
    Explanations

    certain punctuation marks and their usage within sentences

    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
    AndEndTag
    -0.55
     שוליים
    -0.51
    الحياه
    -0.39
    存于互联网档案馆
    -0.39
     estekak
    -0.39
    dafx
    -0.38
    Vidite
    -0.38
    \}\\
    -0.37
     تكبرها
    -0.37
     ujednoznacz
    -0.36
    POSITIVE LOGITS
    AccessorTable
    0.54
    ThroughAttribute
    0.45
    FieldBuilder
    0.44
    StructEnd
    0.43
    MessageTagHelper
    0.42
    Карьера
    0.40
    ardige
    0.40
    RegressionTest
    0.40
     Kara
    0.40
    Largeur
    0.40
    Activations Density 0.298%

    No Known Activations