© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6182
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation in the context of equations

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

    Mathematical notation containing "Tr" or "Vol"

    np_acts-logits-general · gemini-2.0-flash

    {\mathrm{Tr}}, {\mathrm{Vol}}, \mathrm{d}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.82
     MainAxisSize
    -0.69
    rungsseite
    -0.69
    RegressionTest
    -0.68
    iſen
    -0.66
    @@@@@@@@
    -0.66
    tagHelperRunner
    -0.66
    }),
    -0.65
    PerformLayout
    -0.65
    onOptions
    -0.63
    POSITIVE LOGITS
    {
    0.84
    {~
    0.57
    s
    0.54
    <strong>
    0.52
    <b>
    0.48
     nanny
    0.48
    (
    0.48
    -
    0.47
    ic
    0.47
    <sub>
    0.46
    Activations Density 0.230%

    No Known Activations