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. 4787
    Prev
    Next
    INDEX
    Explanations

    references to influential figures in personal development and self-help

    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
    httphttps
    -0.82
     Exacts
    -0.68
    ectoria
    -0.64
    KommentareTeilen
    -0.63
     للاسماء
    -0.61
     pinulongan
    -0.61
     otomatig
    -0.60
    twimg
    -0.57
    Ours
    -0.56
    юрпри
    -0.55
    POSITIVE LOGITS
     coaching
    0.82
     mastermind
    0.74
     coach
    0.69
     coaches
    0.69
     NLP
    0.67
     Coaching
    0.66
    affiliate
    0.66
     affiliate
    0.64
    COACH
    0.63
     Mindset
    0.63
    Activations Density 0.368%

    No Known Activations