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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15360
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare roles and responsibilities

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

    ICU and mechanical ventilation

    np_acts-logits-general · gemini-2.0-flash

    mechanically ventilated patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.47
    RectangleBorder
    -0.38
     jadx
    -0.34
    DrawerToggle
    -0.32
     tal
    -0.31
     '\\;'
    -0.31
    Cordialement
    -0.30
    AutoField
    -0.30
     benne
    -0.29
     autoridade
    -0.29
    POSITIVE LOGITS
     ICU
    1.08
     Intensive
    1.05
     ventilator
    1.01
    ICU
    0.97
     intensive
    0.97
     intensiv
    0.93
     Critical
    0.92
     critically
    0.91
     critical
    0.91
    Critical
    0.89
    Activations Density 0.430%

    No Known Activations