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. 14146
    Prev
    Next
    INDEX
    Explanations

    function and DOM manipulation related keywords in JavaScript

    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
     (_)
    -0.75
     <<<<<<<<<<<<<<
    -0.61
     Takt
    -0.58
     AssemblyCulture
    -0.57
    ρών
    -0.56
    !*\
    -0.55
    はじめに
    -0.55
    twimg
    -0.55
     صوتيه
    -0.55
     bren
    -0.54
    POSITIVE LOGITS
    HasAnnotation
    0.72
    IsPostBack
    0.55
    GetMapping
    0.51
    ('
    0.50
    AutoField
    0.50
     referrerpolicy
    0.49
    HasColumnName
    0.48
    PostMapping
    0.48
    openzeppelin
    0.47
    takings
    0.46
    Activations Density 0.067%

    No Known Activations