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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 751
    Prev
    Next
    INDEX
    Explanations

    references to inspiration and influence in artistic or literary contexts

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

    Inspired by/inspiration

    np_acts-logits-general · gemini-2.0-flash

    inspired by or drawing from

    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
     comigo
    -0.61
     dramatique
    -0.59
     ordinaires
    -0.57
     normaux
    -0.57
     automatiques
    -0.57
     culturelles
    -0.56
     réguli
    -0.56
     vœux
    -0.54
     ويكيميديا
    -0.54
     sulfu
    -0.54
    POSITIVE LOGITS
     inspiration
    2.22
     inspired
    1.92
     inspirations
    1.90
    inspiration
    1.88
     influences
    1.83
     Inspiration
    1.81
    Inspiration
    1.81
     influence
    1.76
     influenced
    1.71
    inspired
    1.68
    Activations Density 0.348%

    No Known Activations