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. 3193
    Prev
    Next
    INDEX
    Explanations

    elements related to viral social media content and controversies surrounding public figures

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

    viral online content

    np_acts-logits-general · gemini-2.0-flash

    viral memes and trending videos

    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
     Stern
    -0.52
    crits
    -0.50
    pova
    -0.49
    versammlung
    -0.48
    InstanceState
    -0.47
     içi
    -0.47
    딩
    -0.47
     rivista
    -0.44
     khỏe
    -0.44
    Profiler
    -0.44
    POSITIVE LOGITS
     viral
    1.82
     Viral
    1.58
    viral
    1.48
    Viral
    1.46
     trending
    1.45
     Trending
    1.09
    trending
    1.08
     circulating
    1.01
     VIR
    1.00
     trend
    0.99
    Activations Density 0.107%

    No Known Activations