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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2044
    Prev
    Next
    INDEX
    Explanations

    references to influential artists and creative inspirations in the context of writing and music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ويكيميديا
    -0.56
     TMPro
    -0.55
    igshid
    -0.52
     automatiques
    -0.50
     dramatique
    -0.50
     triom
    -0.49
    ハツ
    -0.49
     papy
    -0.49
    Demografie
    -0.48
    WindowConstants
    -0.48
    POSITIVE LOGITS
     inspiration
    2.39
     inspirations
    2.06
    inspiration
    2.02
     inspired
    1.91
     Inspiration
    1.89
     influences
    1.86
    Inspiration
    1.83
     inspira
    1.79
     influence
    1.75
     inspiração
    1.70
    Activations Density 0.288%

    No Known Activations