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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10088
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cardiac conditions and complications

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

    Cardiac and ventricular measurements

    np_acts-logits-general · gemini-2.0-flash

    cardiac and ventricular conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kun
    -0.48
    Punt
    -0.46
     rambut
    -0.45
     kon
    -0.45
    Blind
    -0.44
     Schwe
    -0.44
     Blind
    -0.44
    ReusableCell
    -0.43
     Günther
    -0.42
     blind
    -0.42
    POSITIVE LOGITS
     cardiac
    1.04
     Cardiac
    1.00
     echocardio
    0.99
     heart
    0.95
     cardio
    0.94
    ocardio
    0.94
    Cardio
    0.94
    Cardiac
    0.94
     Cardio
    0.93
    cardio
    0.93
    Activations Density 0.573%

    No Known Activations