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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1580
    Prev
    Next
    INDEX
    Explanations

    references to fire incidents and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carriera
    -0.38
    assertAll
    -0.36
     rasanya
    -0.35
     cappuccio
    -0.35
    Millan
    -0.34
    Cartney
    -0.34
     sentada
    -0.34
    疲れ
    -0.34
     суп
    -0.34
     Esses
    -0.33
    POSITIVE LOGITS
     fire
    1.26
     flames
    1.09
     Fire
    1.09
     incendio
    1.08
     fires
    1.03
    Fire
    1.00
     arson
    0.97
     flame
    0.96
     incendi
    0.93
     burning
    0.91
    Activations Density 0.170%

    No Known Activations