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. 20-GEMMASCOPE-RES-16K
    6. 1771
    Prev
    Next
    INDEX
    Explanations

    terms related to heart health and emotional expressions

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

    "heart" and related terms

    np_acts-logits-general · gemini-2.0-flash

    heart rate, breaker, sensor, warmer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.87
    yntaxException
    -0.75
     للمعارف
    -0.72
    URLException
    -0.68
     صوتيه
    -0.67
     فريبيس
    -0.67
     Monfieur
    -0.67
    ‍♀️
    -0.65
    expandindo
    -0.65
     differentiating
    -0.64
    POSITIVE LOGITS
     HEART
    0.89
     hearts
    0.86
     heart
    0.86
     Heart
    0.84
    Hearts
    0.80
     Hearts
    0.80
    hearts
    0.78
    Heart
    0.76
    beat
    0.75
    HEART
    0.74
    Activations Density 0.059%

    No Known Activations