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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 11129
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring and supervision of health or clinical practices

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

    observation or supervision

    np_acts-logits-general · gemini-2.0-flash

    keeping close watch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.66
    UpInside
    -0.57
    abestanden
    -0.52
    UPAC
    -0.49
    AtIndexPath
    -0.49
    PMailer
    -0.49
    uxxxx
    -0.47
    äsident
    -0.47
    etCode
    -0.46
    Autoritní
    -0.45
    POSITIVE LOGITS
     monitoring
    2.73
     monitor
    2.49
     Monitoring
    2.44
    Monitoring
    2.32
     monitors
    2.27
     monitored
    2.24
    monitoring
    2.24
     Monitor
    2.18
    monitor
    2.16
    Monitor
    2.07
    Activations Density 0.496%

    No Known Activations