Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3098
    Prev
    Next
    INDEX
    Explanations

    concepts related to the Internet of Things and digital technologies

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

    "device", "sensor", or "cell"

    np_acts-logits-general · gemini-2.0-flash

    Internet of Things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onAnimation
    -0.68
    mployment
    -0.68
     betweenstory
    -0.66
     ModelExpression
    -0.63
     تانيه
    -0.62
     cinematogra
    -0.59
    новништво
    -0.58
     Paglinawan
    -0.58
     SDLK
    -0.57
     Kosher
    -0.57
    POSITIVE LOGITS
     IoT
    0.88
     sensor
    0.76
    IoT
    0.72
     Sensor
    0.70
     device
    0.67
    iot
    0.66
    mqtt
    0.62
     devices
    0.61
    Sensor
    0.61
     Device
    0.61
    Activations Density 0.389%

    No Known Activations