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. 5-GEMMASCOPE-RES-16K
    6. 13178
    Prev
    Next
    INDEX
    Explanations

    structures and methods related to programming, particularly in object-oriented code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.73
    AutoScale
    -0.62
     ostavi
    -0.61
    djangoproject
    -0.61
    trust
    -0.57
    }{*}{}
    -0.56
    GraphicsUnit
    -0.55
    קישורים
    -0.55
    Utf
    -0.54
    }));
    
    -0.53
    POSITIVE LOGITS
    														
    1.03
    															
    1.01
    													
    0.97
    																
    0.89
    											
    0.87
    												
    0.82
    										
    0.80
    																	
    0.79
    									
    0.76
    UrlResolution
    0.75
    Activations Density 0.397%

    No Known Activations