© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108544
    Prev
    Next
    INDEX
    Explanations

    terminology related to evaporation and humidification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    BagConstraints
    -0.61
    ankin
    -0.41
    webElementXpaths
    -0.41
    skrä
    -0.41
     Position
    -0.40
     Felic
    -0.40
    hlin
    -0.39
    FEL
    -0.39
     Fines
    -0.39
    imens
    -0.38
    POSITIVE LOGITS
    Evaporation
    0.97
     evaporation
    0.92
    potranspiration
    0.89
     Evaporation
    0.80
     evaporate
    0.75
     evapor
    0.72
     Evapor
    0.64
     evaporated
    0.63
    aporation
    0.62
    transpiration
    0.51
    Activations Density 0.009%

    No Known Activations