© 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. 11-GEMMASCOPE-RES-16K
    11. 5076
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to structured sets or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.99
     increí
    -0.95
     témoig
    -0.94
    iſen
    -0.94
     فريبيس
    -0.92
     zuſammen
    -0.92
    ðsíða
    -0.91
    <unused51>
    -0.90
    <unused8>
    -0.90
    <unused14>
    -0.90
    POSITIVE LOGITS
    {
    0.90
    s
    0.57
    <b>
    0.57
    <strong>
    0.56
    <em>
    0.49
    <i>
    0.48
    <u>
    0.46
    ('
    0.45
    {'
    0.44
    {\
    0.44
    Activations Density 0.136%

    No Known Activations