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. 2014
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions, particularly those involving costs, services, and guarantees

    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
    SuspendLayout
    -0.46
    bbl
    -0.44
    üf
    -0.43
     esternos
    -0.41
     насељу
    -0.41
     manus
    -0.41
    JspWriter
    -0.40
    annica
    -0.39
    linge
    -0.39
    ivotopis
    -0.39
    POSITIVE LOGITS
     free
    3.31
    free
    2.96
     FREE
    2.80
    Free
    2.70
    FREE
    2.69
     Free
    2.68
     gratis
    2.39
    免费
    2.17
     gratuitement
    2.13
     беспла
    2.11
    Activations Density 0.251%

    No Known Activations