© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3266
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fire" and related terms throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to fire or firefighting.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     везе
    -0.57
     Kuan
    -0.57
     Nook
    -0.56
    Stefan
    -0.56
    meau
    -0.55
    aspetto
    -0.55
    ViewInit
    -0.54
     LNB
    -0.54
    StructEnd
    -0.54
    agus
    -0.52
    POSITIVE LOGITS
     Fire
    1.14
     fire
    1.09
    Fire
    1.08
     FIRE
    0.97
    fire
    0.90
    FIRE
    0.88
     incendio
    0.78
     fuego
    0.74
     fires
    0.71
     Fires
    0.69
    Activations Density 0.070%

    No Known Activations