© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72189
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal surveillance and its implications for privacy and freedom

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

    government surveillance and control

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of surveillance, privacy invasion, or tracking (e.g., mass/personal surveillance, cameras, license-plate readers, access to private data).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     HasFactory
    -0.50
    IGraphics
    -0.42
    adaptiveStyles
    -0.42
    autorest
    -0.41
    marvin
    -0.41
    ReusableCell
    -0.39
    IsMutable
    -0.38
    概
    -0.37
    REFRESH
    -0.37
     useAppContext
    -0.37
    POSITIVE LOGITS
    Билгалдахарш
    0.57
    Sklici
    0.47
    FieldDescriptor
    0.46
    SuspendLayout
    0.45
    脚注の使い方
    0.45
    Przypisy
    0.40
    Portale
    0.40
     '{@
    0.39
    postsleuth
    0.38
     totalitarian
    0.37
    Activations Density 0.072%

    No Known Activations