© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7996
    Prev
    Next
    INDEX
    Explanations

    references to the concept of burning in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aleg
    -0.43
    Vía
    -0.36
     tout
    -0.35
     aeg
    -0.34
    Terri
    -0.33
    zepine
    -0.33
     apla
    -0.33
     Biological
    -0.32
     private
    -0.32
     Silver
    -0.31
    POSITIVE LOGITS
     burn
    1.55
    burn
    1.31
     Burn
    1.20
    Burn
    1.16
     BURN
    1.13
     burns
    1.11
    BURN
    1.10
     burning
    1.05
    burning
    1.02
     burned
    0.97
    Activations Density 0.249%

    No Known Activations