© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12488
    Prev
    Next
    INDEX
    Explanations

    references to COM ports and their associated components in technical contexts

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

    COM port

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     bienven
    -0.39
    Cuándo
    -0.39
    Prueba
    -0.39
     Italijani
    -0.38
     bienvenida
    -0.38
     Sheppard
    -0.36
     Prueba
    -0.36
     descuento
    -0.35
     emergency
    -0.35
     उत्त
    -0.34
    POSITIVE LOGITS
     COM
    1.48
    COM
    1.05
     ComVisible
    1.00
     Com
    0.94
    Com
    0.88
    com
    0.77
     com
    0.68
    coms
    0.65
     NSCoder
    0.64
     Comm
    0.63
    Activations Density 0.003%

    No Known Activations