© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure

    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
     piele
    -0.49
     noastre
    -0.40
     MaterialApp
    -0.39
    OuterClass
    -0.37
    山形
    -0.37
     nationalists
    -0.36
     yıllar
    -0.35
    úly
    -0.35
     lược
    -0.35
     rilas
    -0.35
    POSITIVE LOGITS
    出版年
    1.15
    tagHelperRunner
    1.07
    UnsafeEnabled
    1.06
     незавершена
    0.93
    elemField
    0.88
    ScopeManager
    0.82
    хьтан
    0.81
    +:+
    0.81
     للاسماء
    0.77
     lenker
    0.76
    Activations Density 0.015%

    No Known Activations