© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10749
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements in code or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     taught
    -0.43
     ve
    -0.40
     Taught
    -0.40
     betweenstory
    -0.39
     so
    -0.39
     sez
    -0.38
    arResult
    -0.37
     qui
    -0.36
     hand
    -0.36
     Paul
    -0.36
    POSITIVE LOGITS
    oredCriteria
    1.04
    addCriterion
    0.88
     <>",
    0.76
    webElementXpaths
    0.67
     <=",
    0.62
    OGND
    0.60
    mbggenerated
    0.59
     autorytatywna
    0.59
     الرياضيه
    0.59
    MigrationBuilder
    0.58
    Activations Density 0.005%

    No Known Activations