© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14447
    Prev
    Next
    INDEX
    Explanations

    the presence of structural or formatting elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Weing
    -0.86
    ajuato
    -0.81
    [...]
    -0.77
     Villanueva
    -0.76
    íncia
    -0.76
    entown
    -0.76
     McColl
    -0.75
    çalves
    -0.75
    MessageTagHelper
    -0.74
     Hilde
    -0.74
    POSITIVE LOGITS
     Carter
    0.81
     Reak
    0.77
    Reak
    0.73
     Fen
    0.73
     Pap
    0.73
     Syr
    0.73
    RetentionPolicy
    0.71
    Carter
    0.70
    carter
    0.69
     Bos
    0.69
    Activations Density 0.011%

    No Known Activations