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. 13877
    Prev
    Next
    INDEX
    Explanations

    references to political events and commentary

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

    specific years

    np_acts-logits-general · gemini-2.0-flash

    politicians and athletes

    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
    https
    -1.11
     covid
    -1.07
     COVID
    -1.04
     https
    -1.04
    covid
    -1.01
     nullptr
    -1.00
     Covid
    -0.99
     🥰
    -0.98
    ttps
    -0.98
    COVID
    -0.97
    POSITIVE LOGITS
    myspace
    0.98
     iPod
    0.96
     = 
    0.90
     idéia
    0.90
     MySpace
    0.86
     Wii
    0.84
     Obama
    0.84
     xrange
    0.83
    iPod
    0.81
     Sarkozy
    0.81
    Activations Density 1.266%

    No Known Activations