© 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. 16-GEMMASCOPE-RES-65K
    11. 31602
    Prev
    Next
    INDEX
    Explanations

    various instances of the beginning of sections or paragraphs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.97
     Jefus
    -0.86
     themſelves
    -0.76
     myſelf
    -0.76
     Reſ
    -0.75
     Anſ
    -0.75
     Majefty
    -0.75
     itſelf
    -0.75
     Theſe
    -0.71
     ſta
    -0.71
    POSITIVE LOGITS
     Malta
    0.76
    Ħ
    0.73
    Malta
    0.72
     Maltese
    0.70
    ħ
    0.69
     malta
    0.57
    ġ
    0.57
    ↵
    0.57
    ċ
    0.57
    0.56
    Activations Density 0.005%

    No Known Activations