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. 11-GEMMASCOPE-RES-16K
    6. 5534
    Prev
    Next
    INDEX
    Explanations

    components related to monitoring devices and tracking technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    WebServlet
    -0.64
    Vorlage
    -0.59
    IsContent
    -0.58
    ijoje
    -0.54
     Pareto
    -0.53
    elevator
    -0.52
     елның
    -0.52
    tió
    -0.51
     firewall
    -0.51
    oleum
    -0.50
    POSITIVE LOGITS
     sensors
    0.93
     devices
    0.83
     sensor
    0.80
     sensores
    0.73
     device
    0.73
     monitoring
    0.71
     Sensors
    0.70
    GEBURTSDATUM
    0.68
     Devices
    0.64
     Sensor
    0.63
    Activations Density 0.698%

    No Known Activations