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. 2297
    Prev
    Next
    INDEX
    Explanations

    references to specific sports events and players

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

    Followed by a preposition or verb

    np_acts-logits-general · gemini-2.0-flash

    in Brighton, Earth, Rio

    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
    tvguidetime
    -1.21
     metaverse
    -1.00
     Metaverse
    -0.98
     pandemic
    -0.96
    covid
    -0.95
    Covid
    -0.92
     TikTok
    -0.91
     Covid
    -0.91
     covid
    -0.89
    pandemic
    -0.89
    POSITIVE LOGITS
     xrange
    1.05
     http
    0.77
     ۲۰۱
    0.72
     Huffington
    0.70
    iteritems
    0.68
     ২০১
    0.61
    SaveSave
    0.60
     Ebola
    0.59
    goo
    0.57
    http
    0.57
    Activations Density 0.631%

    No Known Activations