© 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. 7-GEMMASCOPE-RES-16K
    11. 15624
    Prev
    Next
    INDEX
    Explanations

    references to "root" objects and their systems, indicating a focus on mathematical or programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.79
     autorytatywna
    -0.69
    AndEndTag
    -0.67
    TagMode
    -0.62
    ьаж
    -0.59
     للمعارف
    -0.57
    Vidite
    -0.57
    PMailer
    -0.56
     jsonData
    -0.56
    Gambas
    -0.54
    POSITIVE LOGITS
     root
    3.13
    root
    2.89
     Root
    2.81
    Root
    2.78
     roots
    2.41
     ROOT
    2.39
    ROOT
    2.34
    roots
    2.11
     Roots
    2.09
    根
    2.00
    Activations Density 0.231%

    No Known Activations