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. 7525
    Prev
    Next
    INDEX
    Explanations

    JavaScript function declarations and return statements

    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
    AndEndTag
    -0.81
     betweenstory
    -0.71
    EndContext
    -0.69
    PhysRevD
    -0.68
    WireFormatLite
    -0.68
     مشين
    -0.67
    ?
    
    -0.67
    PhysRev
    -0.66
    MessageTagHelper
    -0.65
     houſe
    -0.65
    POSITIVE LOGITS
     (
    0.85
    (
    0.63
     (<
    0.48
    ((
    0.46
    ([
    0.45
    ValueGenerated
    0.45
    ($
    0.45
     ($
    0.44
    (
    
    0.43
    ^{(
    0.43
    Activations Density 0.052%

    No Known Activations