© 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. 18-GEMMASCOPE-RES-16K
    11. 4157
    Prev
    Next
    INDEX
    Explanations

    references to international publications and organizations

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

    "International" followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    International entities and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.81
     initComponents
    -0.81
     resourceCulture
    -0.75
    SourceChecksum
    -0.73
     kasarigan
    -0.72
    LogFactory
    -0.70
    DatabaseError
    -0.69
    rungsseite
    -0.67
    InjectAttribute
    -0.67
    ValueStyle
    -0.67
    POSITIVE LOGITS
    ization
    0.80
    ized
    0.63
     Zang
    0.58
    isation
    0.58
    ised
    0.56
    ize
    0.55
     bestselling
    0.52
    ędzynarod
    0.52
    arası
    0.52
     Dada
    0.52
    Activations Density 0.061%

    No Known Activations