© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3126
    Prev
    Next
    INDEX
    Explanations

    terms associated with medical and emergency services, particularly relating to burns and surgeries

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ddelweddau
    -0.39
    findpost
    -0.35
     Heinemann
    -0.35
     sofia
    -0.34
    clusal
    -0.34
    WillAppear
    -0.33
    #+#
    -0.33
    windowFixed
    -0.33
    djangoproject
    -0.33
    ativis
    -0.32
    POSITIVE LOGITS
     burn
    3.06
     burned
    2.91
     burning
    2.81
     burns
    2.80
     Burn
    2.75
     burnt
    2.69
    Burn
    2.66
     BURN
    2.50
     Burning
    2.47
    burn
    2.44
    Activations Density 0.431%

    No Known Activations