© 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. 161
    Prev
    Next
    INDEX
    Explanations

    information related to privacy policies and user data management

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

    references to privacy, policies, and user awareness in technology contexts

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

    tech companies and structured data

    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
     الحره
    -0.70
    Contactez
    -0.62
    :✨
    -0.59
     ایشان
    -0.58
    posedge
    -0.57
     contacter
    -0.57
    Heraus
    -0.55
     Trouver
    -0.55
    Dziękuję
    -0.54
    ükemmel
    -0.54
    POSITIVE LOGITS
     users
    0.86
     Microsoft
    0.82
     Apple
    0.80
     Google
    0.80
     Users
    0.77
    Google
    0.77
    Microsoft
    0.75
    Users
    0.74
    Apple
    0.70
     analysts
    0.67
    Activations Density 0.092%

    No Known Activations