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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2014
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical kernels and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PrintWriter
    -0.47
    PMID
    -0.42
     fVar
    -0.41
    клопе
    -0.41
     extras
    -0.41
    日閲覧
    -0.40
    TagMode
    -0.40
     ModelAndView
    -0.40
     aVar
    -0.40
     createSprite
    -0.40
    POSITIVE LOGITS
     ker
    1.98
    Ker
    1.91
     Ker
    1.87
    ker
    1.86
     KER
    1.62
    KER
    1.61
    kers
    1.11
     Кер
    1.01
    кер
    1.00
    кера
    0.93
    Activations Density 0.389%

    No Known Activations