© 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. 1-GEMMASCOPE-RES-16K
    11. 10103
    Prev
    Next
    INDEX
    Explanations

    references to physical edges or borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.79
    ToScroll
    -0.70
     näin
    -0.65
    romyal
    -0.64
    umato
    -0.63
    xmlWriter
    -0.63
    atelyn
    -0.63
    AndEndTag
    -0.62
    publique
    -0.62
     blogging
    -0.61
    POSITIVE LOGITS
     edge
    4.56
     Edge
    4.28
    edge
    4.22
    Edge
    4.11
     EDGE
    3.72
    EDGE
    3.56
     edges
    3.12
     Edges
    2.85
    edges
    2.73
    Edges
    2.59
    Activations Density 0.074%

    No Known Activations