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. 20-GEMMASCOPE-RES-16K
    6. 12611
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to negligence and medical emergencies.

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

    situations related to medical emergencies and legal cases.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of calling for emergency services or assistance, particularly in medical or crisis situations.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Dispatching emergency services

    np_acts-logits-general · gemini-2.0-flash

    calling for emergency services

    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
     CURIAM
    -0.84
    Portail
    -0.82
    fjspx
    -0.81
    IsContent
    -0.71
    IBOutlet
    -0.71
    kháu
    -0.71
     HttpNotFound
    -0.67
     Roskov
    -0.66
    twimg
    -0.66
     lccn
    -0.65
    POSITIVE LOGITS
     emergency
    1.88
     Emergency
    1.59
    Emergency
    1.54
    emergency
    1.52
     EMERGENCY
    1.48
     emergencies
    1.32
    EMERGENCY
    1.28
     paramedics
    1.25
     ambulance
    1.21
     Ambulance
    1.12
    Activations Density 0.237%

    No Known Activations