© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6848
    Prev
    Next
    INDEX
    Explanations

    terms related to fuel cells and their applications

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

    "fuel" or "fuel cell"

    np_acts-logits-general · gemini-2.0-flash

    fuel cells, oil, injection, consumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.88
    thâu
    -0.80
    AccessorTable
    -0.75
    SpringBootTest
    -0.73
    ⓧ
    -0.73
    findpost
    -0.70
    chyma
    -0.69
    ViewFeatures
    -0.67
    bosis
    -0.67
    ulism
    -0.66
    POSITIVE LOGITS
     fuel
    1.11
     Fuel
    0.98
    fuel
    0.98
    Fuel
    0.97
     fuels
    0.96
    FUEL
    0.93
     FUEL
    0.92
     Fuels
    0.75
    燃料
    0.73
     fueled
    0.72
    Activations Density 0.089%

    No Known Activations