© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and demographics

    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
    complexContent
    -0.76
     vectorielle
    -0.72
     للاسماء
    -0.71
     disambiguazione
    -0.69
     Sudanese
    -0.65
     Latvian
    -0.65
     vettor
    -0.64
     Cheshire
    -0.62
     Athenians
    -0.62
    RenderAtEndOf
    -0.62
    POSITIVE LOGITS
    +#+
    0.58
     United
    0.50
    transQ
    0.47
     USA
    0.47
    PYX
    0.45
    rrggbb
    0.44
     European
    0.43
    uelto
    0.43
    Initializable
    0.41
     DbSet
    0.40
    Activations Density 0.338%

    No Known Activations