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. 6707
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    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
    ViewFeatures
    -0.77
    LEGGI
    -0.64
     BoxDecoration
    -0.61
    CppMethod
    -0.57
    ?')
    -0.56
    PositiveButton
    -0.55
    XmlElement
    -0.55
     CreateTagHelper
    -0.54
    ?”,
    -0.54
    basicConfig
    -0.54
    POSITIVE LOGITS
     <
    0.74
    tvguidetime
    0.72
     PhpStorm
    0.72
    code
    0.69
     code
    0.68
    Code
    0.66
     */
    0.64
    Coder
    0.64
    <\
    0.63
     Code
    0.61
    Activations Density 0.259%

    No Known Activations