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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 13720
    Prev
    Next
    INDEX
    Explanations

    references to community organizations and involvement in social activities

    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
    contentLoaded
    -0.71
    AddTagHelper
    -0.64
     AssemblyTitle
    -0.59
    ppelin
    -0.56
    Viited
    -0.54
    IsContent
    -0.53
    URLException
    -0.52
    efully
    -0.50
     &___
    -0.50
    ंदीखरीदारी
    -0.48
    POSITIVE LOGITS
     club
    1.39
     clubs
    1.22
     Club
    1.20
    club
    1.17
     association
    1.15
    Club
    1.13
     CLUB
    1.08
     associations
    1.06
    CLUB
    1.02
     Association
    1.00
    Activations Density 0.332%

    No Known Activations