© 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. 18-GEMMASCOPE-RES-16K
    11. 1900
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental pollution and mitigation strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pollution or contaminants

    np_acts-logits-general · gemini-2.0-flash

    environmental pollution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.71
     NSCoder
    -0.62
    WriteBarrier
    -0.61
    Hentet
    -0.58
    StoryboardSegue
    -0.57
    })*/
    -0.57
     препратки
    -0.57
    adaptiveStyles
    -0.56
    śmie
    -0.56
    EndGlobalSection
    -0.56
    POSITIVE LOGITS
     pollution
    1.31
     polluted
    1.20
     environmental
    1.18
     Pollution
    1.18
    Pollution
    1.10
     Environmental
    1.08
     contaminated
    1.08
     pollutants
    1.06
    pollution
    1.04
     pollutant
    1.02
    Activations Density 0.336%

    No Known Activations