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. 9199
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming-related structures

    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
     ()=>{
    -0.77
      
    -0.77
     ()=>
    -0.77
    ={()=>
    -0.72
    ="'+
    -0.70
     میتوان
    -0.70
    
    -0.66
     میشود
    -0.64
    [:,:,
    -0.64
     میکن
    -0.62
    POSITIVE LOGITS
     //
    
    0.66
     XNUMX
    0.64
    tvguidetime
    0.64
     />}
    0.63
     ─
    0.59
    .}}
    0.57
    .")
    
    0.57
     NgModule
    0.56
     =
    
    0.55
     ↓,
    0.54
    Activations Density 0.291%

    No Known Activations