© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses, particularly related to technical specifications and classifications

    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
    Дереккөздер
    -0.79
    脚注の使い方
    -0.73
    ConstraintMaker
    -0.72
     ddelweddau
    -0.70
    olesale
    -0.69
     Efq
    -0.67
     astray
    -0.66
     opérateur
    -0.66
    +#+#
    -0.66
    nefs
    -0.65
    POSITIVE LOGITS
     (
    0.63
    (
    0.54
    简称
    0.50
    （
    0.45
     [
    0.43
     (“
    0.43
    modi
    0.42
     ("
    0.41
     abbreviated
    0.40
    ("
    0.40
    Activations Density 0.215%

    No Known Activations