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. 7849
    Prev
    Next
    INDEX
    Explanations

    references to emergency medical situations and treatments

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

    Emergency medical situations and response

    np_acts-logits-general · gemini-2.0-flash

    emergency medical care and services

    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
     <=",
    -0.58
    gout
    -0.55
     câte
    -0.55
     Deletion
    -0.55
     deletions
    -0.52
     CURIAM
    -0.52
    orestation
    -0.51
     avsl
    -0.51
     HttpNotFound
    -0.50
     typelib
    -0.50
    POSITIVE LOGITS
     emergency
    1.86
     Emergency
    1.69
    Emergency
    1.56
    emergency
    1.50
     EMERGENCY
    1.42
     emergencies
    1.28
     ambulance
    1.27
     rescue
    1.23
     paramedics
    1.21
     Ambulance
    1.19
    Activations Density 0.226%

    No Known Activations