© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    references to mythical or fantastical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and proper nouns across various texts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     adecu
    -0.35
    wój
    -0.32
     totul
    -0.31
     relevant
    -0.31
    ądź
    -0.31
     temor
    -0.30
     Justicia
    -0.30
     Bélgica
    -0.30
     Canadá
    -0.29
     Etats
    -0.29
    POSITIVE LOGITS
     protoimpl
    1.04
    parsedMessage
    1.00
     ویکی‌پدی
    0.98
    RegressionTest
    0.95
    تقاوى
    0.89
     مشين
    0.87
    دانشنامهٔ
    0.82
    
    0.81
    webElementXpaths
    0.78
    sizeCache
    0.77
    Activations Density 0.007%

    No Known Activations