© 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. 8468
    Prev
    Next
    INDEX
    Explanations

    patterns indicating the presence of numerical data or statistical results

    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
    adaptiveStyles
    -0.79
    uxxxx
    -0.73
     المعيارى
    -0.68
    étoit
    -0.65
    contentLoaded
    -0.65
     kasarigan
    -0.64
     Normdatei
    -0.62
     otomatig
    -0.62
    vrolet
    -0.60
    #+#
    -0.60
    POSITIVE LOGITS
    ification
    0.43
    fjspx
    0.36
     App
    0.35
     Dog
    0.33
     Hall
    0.33
     fabric
    0.33
     Gera
    0.32
     Main
    0.31
     King
    0.31
     mon
    0.31
    Activations Density 0.499%

    No Known Activations