© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 13933
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IContainer
    -0.97
     betweenstory
    -0.94
    الدراسه
    -0.91
     itſelf
    -0.89
    InjectAttribute
    -0.86
     RSSSF
    -0.84
     cdti
    -0.84
     Chriftian
    -0.82
     quæ
    -0.82
     fubject
    -0.82
    POSITIVE LOGITS
     really
    0.85
     the
    0.85
     a
    0.81
     what
    0.78
     real
    0.74
     not
    0.73
     an
    0.73
     truly
    0.70
     all
    0.68
     one
    0.67
    Activations Density 0.036%

    No Known Activations