© 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. 3-GEMMASCOPE-RES-16K
    11. 9107
    Prev
    Next
    INDEX
    Explanations

    references to domestic issues, particularly in relation to violence and social circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.96
    AnimationsModule
    -0.75
    appé
    -0.75
    ]")]
    -0.74
     AssemblyCulture
    -0.74
    $_['
    -0.72
     tokenId
    -0.71
    graphiques
    -0.68
    otheby
    -0.67
    vedra
    -0.65
    POSITIVE LOGITS
     domestic
    3.39
     Domestic
    3.21
    Domestic
    3.12
    domestic
    3.07
     domesti
    2.38
     domestically
    2.34
    ESTIC
    2.07
     domesticated
    1.76
     domestique
    1.74
     doméstico
    1.73
    Activations Density 0.045%

    No Known Activations