© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2681
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation associated with sets and structures

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

    Greek letters followed by subscripts

    np_acts-logits-general · gemini-2.0-flash

    escape, in, ex, dr efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſen
    -1.00
     فريبيس
    -1.00
     témoig
    -0.95
     increí
    -0.94
     zuſammen
    -0.93
    rungsseite
    -0.91
    ſammen
    -0.90
     müſſen
    -0.90
     laſſen
    -0.90
     MainAxisSize
    -0.89
    POSITIVE LOGITS
    {
    0.98
    <strong>
    0.56
    <b>
    0.56
    (
    0.54
    <em>
    0.54
    <i>
    0.52
    s
    0.47
    ('
    0.47
     the
    0.46
    <sub>
    0.46
    Activations Density 0.192%

    No Known Activations