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. 10132
    Prev
    Next
    INDEX
    Explanations

    references to media coverage and its impact on public perception

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

    news and media

    np_acts-logits-general · gemini-2.0-flash

    media attention, news coverage

    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
    Portail
    -0.70
    الحياه
    -0.67
    SharedDtor
    -0.60
    HtmlAttribute
    -0.59
    LLocation
    -0.58
     AssemblyCompany
    -0.55
    SharedCtor
    -0.54
    GIH
    -0.54
    TacToe
    -0.54
     kaarangay
    -0.52
    POSITIVE LOGITS
     media
    1.67
     headlines
    1.58
     news
    1.43
     publicity
    1.41
    media
    1.31
     press
    1.28
     headline
    1.25
     newspapers
    1.23
     tabloid
    1.20
     newspaper
    1.19
    Activations Density 0.449%

    No Known Activations