© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5147
    Prev
    Next
    INDEX
    Explanations

    phrases associated with obituaries and death announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atlántico
    -0.56
    볼
    -0.48
     fare
    -0.48
    IsContent
    -0.47
     observers
    -0.47
     vra
    -0.47
     Observer
    -0.47
    ますが
    -0.47
     sector
    -0.46
     Drapeau
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.89
     unknownFields
    0.70
    DebuggerNonUser
    0.67
     smtplib
    0.64
    Hochspringen
    0.61
     betweenstory
    0.58
     AssemblyCompany
    0.58
    XmlEnum
    0.58
    UnifiedTopology
    0.57
     endwhile
    0.55
    Activations Density 0.015%

    No Known Activations