© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 14980
    Prev
    Next
    INDEX
    Explanations

    terms relating to telecommunications and regulatory issues

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

    Comes after a punctuation mark

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.33
    Према
    -0.32
     расход
    -0.30
    nasel
    -0.28
    AdapterFactory
    -0.27
    iornamento
    -0.27
    Чыганаклар
    -0.26
     Wear
    -0.26
     Audiodateien
    -0.26
     BIM
    -0.26
    POSITIVE LOGITS
     Broadband
    0.94
     broadband
    0.90
     fiber
    0.89
    Fiber
    0.88
     Fiber
    0.86
     telecom
    0.83
     Telecom
    0.83
     fibre
    0.81
    fiber
    0.79
     subscribers
    0.78
    Activations Density 0.423%

    No Known Activations