© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14658
    Prev
    Next
    INDEX
    Explanations

    specific structural elements commonly used in document formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -1.00
    parsedMessage
    -0.98
    出版年
    -0.97
     Wikimedijinoj
    -0.95
    adaptiveStyles
    -0.94
     ujednoznacz
    -0.93
    RegressionTest
    -0.92
    ſammen
    -0.92
     MainAxisSize
    -0.91
    Rujuakan
    -0.89
    POSITIVE LOGITS
    {
    0.70
    9
    0.56
    <
    0.51
    0
    0.49
    1
    0.46
    [
    0.43
     {
    0.43
    <blockquote>
    0.38
    tabular
    0.37
     bedo
    0.36
    Activations Density 0.040%

    No Known Activations