© 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. 0-GEMMASCOPE-RES-16K
    11. 8639
    Prev
    Next
    INDEX
    Explanations

    words related to receptions, events, and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.73
     NSCoder
    -0.71
     Biôgrafia
    -0.68
    PerformLayout
    -0.66
     فريبيس
    -0.65
     endwhile
    -0.63
     שוליים
    -0.62
     lenker
    -0.60
     <",
    -0.59
    onAttach
    -0.59
    POSITIVE LOGITS
     Hon
    0.56
    <code>
    0.54
    ="
    0.53
    <blockquote>
    0.52
    ness
    0.47
    (`
    0.46
    ded
    0.46
    Hon
    0.45
    <table>
    0.43
    ว่า
    0.42
    Activations Density 0.343%

    No Known Activations