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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 13977
    Prev
    Next
    INDEX
    Explanations

    content related to political campaigns and their marketing strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AnchorStyles
    -0.75
    Autoritní
    -0.67
    WSGI
    -0.65
    aspectj
    -0.64
    WebVitals
    -0.63
    +:+
    -0.62
     فريبيس
    -0.60
    openConnection
    -0.58
    saraba
    -0.58
    AnimationsModule
    -0.58
    POSITIVE LOGITS
     leaflets
    1.44
     pamphlets
    1.42
     brochures
    1.42
     leaflet
    1.41
     flyers
    1.38
     pamphlet
    1.33
     brochure
    1.32
     booklets
    1.30
     flyer
    1.29
     booklet
    1.29
    Activations Density 0.290%

    No Known Activations