© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4807
    Prev
    Next
    INDEX
    Explanations

    references to motivation and definitions in the context of gaming and programming

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

    Follows a question mark ":"

    np_acts-logits-general · gemini-2.0-flash

    defining or describing entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.44
     couvercle
    -0.32
     navire
    -0.31
     myſelf
    -0.30
     éclairage
    -0.30
     zusätz
    -0.29
    detectChanges
    -0.28
     mariée
    -0.27
    WriteBarrier
    -0.27
     metálica
    -0.27
    POSITIVE LOGITS
    NameInMap
    0.75
     Walkover
    0.72
    什么是
    0.68
     שוליים
    0.63
    所謂
    0.63
     propOrder
    0.61
     AssemblyCulture
    0.61
     Савезне
    0.61
     sogenannten
    0.57
    writeFieldEnd
    0.56
    Activations Density 1.128%

    No Known Activations