Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5006
    Prev
    Next
    INDEX
    Explanations

    key figures and entities related to environmental policies and events

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

    Follows "the", a number, or a name

    np_acts-logits-general · gemini-2.0-flash

    environmental conservation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CommonModule
    -0.82
    WebVitals
    -0.68
    MethodManager
    -0.68
    bootstrapcdn
    -0.66
     تضيفلها
    -0.65
    PerformLayout
    -0.63
    ométrique
    -0.63
    awtextra
    -0.61
    AndEndTag
    -0.61
    HasAnnotation
    -0.60
    POSITIVE LOGITS
     environmental
    1.54
     conservation
    1.50
     Environmental
    1.39
    Environmental
    1.36
     Conservation
    1.34
    Conservation
    1.29
    environmental
    1.28
    conservation
    1.28
     eco
    1.21
     ecological
    1.17
    Activations Density 0.297%

    No Known Activations