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. 13002
    Prev
    Next
    INDEX
    Explanations

    statistics related to large populations and demographics

    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
    ocarpus
    -0.55
     Luch
    -0.53
    asel
    -0.52
    gulls
    -0.51
    TagHelper
    -0.50
    ✭✭
    -0.48
     مرئيه
    -0.48
    otá
    -0.47
    loca
    -0.47
    存于互联网档案馆
    -0.46
    POSITIVE LOGITS
     millions
    1.33
     Millions
    1.12
    millions
    1.12
     milioni
    1.07
    Millions
    1.05
     millones
    1.05
     milhões
    1.00
     billions
    0.99
     million
    0.99
     milliards
    0.95
    Activations Density 0.202%

    No Known Activations