© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 10045
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and related structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magno
    -0.55
    MAKING
    -0.55
    gameserver
    -0.52
     making
    -0.51
    epam
    -0.50
    udan
    -0.48
     VCR
    -0.48
    copus
    -0.48
     ProgressDialog
    -0.48
    Demografia
    -0.47
    POSITIVE LOGITS
     Efq
    1.08
     myſelf
    1.07
     tfsi
    1.03
     ſeveral
    1.03
     enfans
    1.00
     Theſe
    0.98
     houſe
    0.96
     Shakspeare
    0.96
     leaſt
    0.96
     Majefty
    0.95
    Activations Density 0.019%

    No Known Activations