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. 10149
    Prev
    Next
    INDEX
    Explanations

    structural elements and components in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with brackets and colons

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal and numeric codes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
                    
    -0.89
                     
    -0.84
                   
    -0.84
                  
    -0.84
                 
    -0.80
                      
    -0.79
    				
    -0.78
                       
    -0.77
                
    -0.76
                        
    -0.76
    POSITIVE LOGITS
     виправивши
    1.15
    rungsseite
    1.06
    tvguidetime
    1.05
     lenker
    1.05
    PerformLayout
    1.03
    DockStyle
    1.02
    ArgsConstructor
    1.02
    AndEndTag
    1.00
     beginnetje
    0.97
     '\\;'
    0.93
    Activations Density 0.208%

    No Known Activations