© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5004
    Prev
    Next
    INDEX
    Explanations

    phrases related to oversight and monitoring

    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
     
    -0.60
     u
    -0.59
     ne
    -0.59
    \\
    -0.58
     ké
    -0.58
     z
    -0.58
     r
    -0.57
     ₹
    -0.56
     j
    -0.56
    •
    -0.56
    POSITIVE LOGITS
     monitoring
    1.75
     monitored
    1.67
     monitors
    1.56
    monitoring
    1.53
     monitor
    1.53
     Monitoring
    1.50
     Monitors
    1.46
    itored
    1.43
     MONITORING
    1.41
     MONITOR
    1.40
    Activations Density 0.115%

    No Known Activations