© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1571
    Prev
    Next
    INDEX
    Explanations

    terms related to fire and firefighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.93
    GOTREF
    -0.90
     Jacobsen
    -0.77
    Vea
    -0.72
    onAttach
    -0.71
    ostante
    -0.68
    הערות
    -0.67
     CURIAM
    -0.67
    seamnă
    -0.66
    eraard
    -0.66
    POSITIVE LOGITS
     fire
    3.44
     Fire
    3.19
    Fire
    3.16
    fire
    3.12
     FIRE
    2.94
    FIRE
    2.83
     fires
    2.79
    fires
    2.43
     Fires
    2.39
     fuego
    2.18
    Activations Density 0.044%

    No Known Activations