Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4952
    Prev
    Next
    INDEX
    Explanations

    terms related to fuel cells and their applications

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

    "Fuel cell" or related to fuel

    np_acts-logits-general · gemini-2.0-flash

    fuel cell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    verwijspagina
    -0.73
    BeginContext
    -0.72
    EDEFAULT
    -0.68
    Jeografia
    -0.67
    FunctionFlags
    -0.65
    acek
    -0.65
    thâu
    -0.64
    //
    -0.64
    AccessorTable
    -0.63
    tuan
    -0.62
    POSITIVE LOGITS
     tank
    0.62
     fuel
    0.57
    tanks
    0.54
    ConstraintMaker
    0.54
     supply
    0.54
     Fuel
    0.53
     tanks
    0.52
     Tank
    0.51
    FUEL
    0.50
     TANK
    0.50
    Activations Density 0.125%

    No Known Activations