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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101657
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations commonly used in equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.71
    :✨
    -0.53
    Vidite
    -0.50
     autorytatywna
    -0.49
     مواليد
    -0.48
     utafitiHapana
    -0.47
    Tembelea
    -0.47
    oa̍t
    -0.47
    lgari
    -0.46
     Chwiliwch
    -0.46
    POSITIVE LOGITS
     fordern
    0.43
     pério
    0.42
    synthesize
    0.40
    Pautan
    0.40
     $('#
    0.39
    MessageTagHelper
    0.39
     grève
    0.39
    AutoScale
    0.39
     erleich
    0.35
    invokeLater
    0.35
    Activations Density 1.116%

    No Known Activations