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. 13930
    Prev
    Next
    INDEX
    Explanations

    code structures and programming syntax 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
    <>
    
    -0.71
    ypal
    -0.71
    WebServlet
    -0.70
    pportun
    -0.68
     CreateTagHelper
    -0.67
    Erstellt
    -0.67
     مفص
    -0.66
    jectures
    -0.64
    $$
    
    -0.63
     Ã
    -0.63
    POSITIVE LOGITS
    }
    1.13
    	
    1.00
    )
    0.97
    ↵↵
    0.93
        
    0.91
    </code>
    0.87
    <eos>
    0.85
    }.
    0.85
    ]
    0.85
    。
    0.82
    Activations Density 0.226%

    No Known Activations