© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 9776
    Prev
    Next
    INDEX
    Explanations

    references to international agreements and environmental policies related to ozone depletion and climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.66
    AndEndTag
    -0.64
     Paglinawan
    -0.56
    ρους
    -0.56
    ViewImports
    -0.55
     layui
    -0.55
    RepeatedField
    -0.54
    PRWEB
    -0.54
     مرئيه
    -0.53
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     countries
    1.77
     nations
    1.48
     governments
    1.43
     states
    1.40
    countries
    1.37
     Countries
    1.33
    Countries
    1.25
     States
    1.23
     Governments
    1.21
     COUNTRIES
    1.13
    Activations Density 0.381%

    No Known Activations