© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103889
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables in the context of formal 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
    ParallelGroup
    -0.40
     للاسماء
    -0.35
    urtstag
    -0.34
    出版年
    -0.34
    ox
    -0.32
    yle
    -0.31
    ContentAsync
    -0.31
     camadas
    -0.30
    pon
    -0.30
    CreateTable
    -0.30
    POSITIVE LOGITS
    NUMX
    0.58
    StoryboardSegue
    0.56
     snippetHide
    0.56
     الرياضيه
    0.56
    featureID
    0.56
    質
    0.52
     arşivlendi
    0.52
    typeorm
    0.51
    AnimationsModule
    0.50
    质
    0.48
    Activations Density 0.490%

    No Known Activations