© 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 - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 12919
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WireFormatLite
    -0.74
    ArrowToggle
    -0.68
    ChildScrollView
    -0.65
     kaarangay
    -0.61
    fromCharCode
    -0.60
    RectangleBorder
    -0.59
    (&:
    -0.59
     AspNetCore
    -0.59
     MessageBoxIcon
    -0.58
    complexContent
    -0.58
    POSITIVE LOGITS
     there
    0.82
     it
    0.72
     we
    0.71
    there
    0.64
     they
    0.54
     inilah
    0.53
     you
    0.52
     the
    0.50
    we
    0.46
    the
    0.44
    Activations Density 0.752%

    No Known Activations