© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1850
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent protests and explosive materials

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

    fired or thrown projectiles

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Audiodateien
    -0.75
    tagHelperRunner
    -0.73
     GoogleFonts
    -0.66
     فريبيس
    -0.65
    日閲覧
    -0.59
    setVerticalGroup
    -0.59
     ویکی‌پدی
    -0.53
     Baillargeon
    -0.53
     fathoms
    -0.52
     Normdatei
    -0.52
    POSITIVE LOGITS
     bullet
    0.99
     projectiles
    0.96
     projectile
    0.96
     bullets
    0.95
     thrown
    0.94
     hurled
    0.90
     throwing
    0.86
     flying
    0.85
     threw
    0.83
     throw
    0.82
    Activations Density 0.078%

    No Known Activations