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. 21-GEMMASCOPE-RES-16K
    6. 904
    Prev
    Next
    INDEX
    Explanations

    terms related to fuel and energy systems, particularly fuel cells and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.90
    ⓧ
    -0.75
    enterOuterAlt
    -0.74
    EDEFAULT
    -0.71
     intptr
    -0.69
     AssemblyCulture
    -0.68
    FunctionFlags
    -0.66
    ViewFeatures
    -0.65
    setVerticalGroup
    -0.65
    Tikang
    -0.65
    POSITIVE LOGITS
     consumption
    0.47
     supply
    0.47
     fuel
    0.47
     tank
    0.47
     manhã
    0.46
     efficiency
    0.46
    ądz
    0.45
     fuels
    0.45
     economy
    0.45
    ámara
    0.45
    Activations Density 0.069%

    No Known Activations