© 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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4004
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to photosynthesis and light reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deflation
    -0.68
     CWE
    -0.65
    createTextNode
    -0.56
    SQLException
    -0.55
    ^(@)
    -0.54
    acke
    -0.54
     useState
    -0.54
     SDS
    -0.54
    dataclass
    -0.53
     Sykes
    -0.53
    POSITIVE LOGITS
    Sunlight
    0.91
     Sunlight
    0.78
     sunlight
    0.74
     suns
    0.69
     photosynthesis
    0.69
     phot
    0.62
    asteroide
    0.61
     solares
    0.61
     ultraviolet
    0.60
     UV
    0.60
    Activations Density 0.871%

    No Known Activations