© 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. 21-GEMMASCOPE-RES-16K
    11. 14639
    Prev
    Next
    INDEX
    Explanations

    references to Japan's Prime Ministerial spouses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.80
     Fidel
    -0.70
     apartheid
    -0.64
    достатки
    -0.64
     KGB
    -0.61
    évaluateur
    -0.61
     Khrushchev
    -0.59
    regation
    -0.58
     DialogInterface
    -0.58
     Missile
    -0.58
    POSITIVE LOGITS
    XmlType
    0.68
     propOrder
    0.60
     WWI
    0.54
    Wikis
    0.48
    ghed
    0.45
    DaoImpl
    0.44
    LogManager
    0.44
    Online
    0.44
    Obrázky
    0.43
    EndGlobalSection
    0.42
    Activations Density 0.338%

    No Known Activations