© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13868
    Prev
    Next
    INDEX
    Explanations

    terms related to medical emergencies and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    daging
    -0.42
    がん
    -0.41
     Sc
    -0.39
     She
    -0.39
     she
    -0.39
     copy
    -0.38
    Jealous
    -0.36
     formerly
    -0.36
    rasse
    -0.36
     con
    -0.36
    POSITIVE LOGITS
     service
    0.95
     Ambulance
    0.88
     ambulances
    0.86
     serviced
    0.86
    Tikang
    0.84
    service
    0.83
     SERVICE
    0.83
     services
    0.83
    __":
    0.81
    __':
    0.81
    Activations Density 0.440%

    No Known Activations