© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 1554
    Prev
    Next
    INDEX
    Explanations

    various types of brackets or braces used in mathematical notation

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

    latex labels

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    parsedMessage
    -1.20
     MainAxisSize
    -1.04
    PerformLayout
    -1.01
    IntoConstraints
    -0.99
     незавершена
    -0.90
     témoig
    -0.89
     nakalista
    -0.89
     propOrder
    -0.85
    RegressionTest
    -0.84
    styleType
    -0.83
    POSITIVE LOGITS
    http
    0.70
    <em>
    0.58
    <i>
    0.58
     http
    0.57
    https
    0.56
    <strong>
    0.52
    <b>
    0.52
    {
    0.51
    <u>
    0.48
     direta
    0.48
    Activations Density 0.011%

    No Known Activations