© 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. 7808
    Prev
    Next
    INDEX
    Explanations

    terms related to fire and its effects

    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
     ویکی‌پدی
    -0.59
    GHIJKLM
    -0.51
     AssemblyTitle
    -0.47
     betweenstory
    -0.45
     Autorisations
    -0.45
    ⓘ
    -0.45
     Oce
    -0.44
    endpush
    -0.44
     widgets
    -0.44
     Signalez
    -0.43
    POSITIVE LOGITS
     fire
    1.79
    fire
    1.54
     Fire
    1.50
    FIRE
    1.48
    Fire
    1.46
     FIRE
    1.44
     vuur
    1.37
     fireplace
    1.35
     fires
    1.32
     flame
    1.31
    Activations Density 0.307%

    No Known Activations