© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4445
    Prev
    Next
    INDEX
    Explanations

    references to arXiv preprints and their identifiers

    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
    новништво
    -0.84
    AsUp
    -0.75
     Савезне
    -0.73
    تفصیلات
    -0.70
     هيا
    -0.69
    WithMany
    -0.69
    ToScroll
    -0.67
     Michaelis
    -0.66
    TintMode
    -0.65
    (!__
    -0.63
    POSITIVE LOGITS
    arXiv
    5.55
     arXiv
    1.68
    arxiv
    1.20
    Xiv
    0.96
     arxiv
    0.95
     Arxiv
    0.74
     EconPapers
    0.72
    doi
    0.61
    modelBuilder
    0.58
    /***/
    0.57
    Activations Density 0.022%

    No Known Activations