© 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. 5-GEMMASCOPE-RES-16K
    11. 15836
    Prev
    Next
    INDEX
    Explanations

    references to citing sources or citations within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.77
    findpost
    -0.67
     Hunan
    -0.66
    similiano
    -0.65
     currentIndex
    -0.64
    انجليز
    -0.63
    ($__
    -0.62
     SwiftUI
    -0.62
    owulf
    -0.62
    alanta
    -0.61
    POSITIVE LOGITS
    cite
    2.09
     cite
    1.54
    Cite
    1.53
     Cite
    1.40
    cited
    1.23
     citing
    1.21
     Citation
    1.20
     citations
    1.16
     cited
    1.15
     citation
    1.14
    Activations Density 0.155%

    No Known Activations