© 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. 11-GEMMASCOPE-RES-16K
    6. 12309
    Prev
    Next
    INDEX
    Explanations

    data related to climate change and its environmental impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.80
    RenderAtEndOf
    -0.67
     للمعارف
    -0.66
    hyrchwyd
    -0.59
     '\\;'
    -0.59
    WebElementEntity
    -0.59
     Shreve
    -0.55
    yntaxException
    -0.55
    JspWriter
    -0.55
     HasFactory
    -0.54
    POSITIVE LOGITS
     climate
    0.74
     climático
    0.70
     Climate
    0.69
    Climate
    0.69
    climate
    0.67
     global
    0.64
     CLIMATE
    0.63
     climatic
    0.60
     réfugiés
    0.57
     Climatic
    0.55
    Activations Density 0.141%

    No Known Activations