© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28645
    Prev
    Next
    INDEX
    Explanations

    mentions of fire

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

    fire related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -1.09
     tartalomajánló
    -1.09
    theless
    -0.96
    .}~\
    -0.94
     Roskov
    -0.94
    ItemBackground
    -0.93
    etheless
    -0.91
    PyExc
    -0.90
     Jacobsen
    -0.89
    ]").
    -0.88
    POSITIVE LOGITS
    fire
    1.08
    Fire
    1.05
     FIRE
    1.00
    i
    0.98
     fire
    0.98
     Fire
    0.97
    FIRE
    0.97
    y
    0.96
     fires
    0.96
    火
    0.84
    Activations Density 0.014%

    No Known Activations