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. 6387
    Prev
    Next
    INDEX
    Explanations

    programming structures and control flow elements

    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
    ?
    -0.79
    ')){
    -0.79
     }}{
    -0.77
    '])){
    -0.76
    ']){
    -0.76
    ?\\
    -0.75
    .\\
    -0.75
     ...
    -0.74
    ;
    
    
    -0.73
    '])){
    
    -0.73
    POSITIVE LOGITS
    []
    
    0.72
    )))
    
    0.71
    ()
    
    0.71
    ]))
    
    0.71
    DockStyle
    0.68
    }))
    
    0.66
    "])
    
    0.63
    ")
    
    0.63
     AssemblyTitle
    0.61
    %")
    0.61
    Activations Density 0.106%

    No Known Activations