© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 44
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bos" which likely marks the beginning of a new section or thought in a document

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

    references to coding or programming constructs, specifically related to data structures and functions

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

    answers to some list

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ujednoznacz
    -0.99
    )».
    -0.95
    )»
    -0.95
    )”.
    -0.92
    )";
    -0.91
     />";
    -0.86
    Portale
    -0.86
    )".
    -0.84
     />';
    -0.83
     $_"
    -0.83
    POSITIVE LOGITS
    ↵
    0.71
      
    0.67
    0.55
     numOf
    0.51
     acordo
    0.50
     idk
    0.49
    储存
    0.47
     

    0.47
    </h2>
    0.47
    	
    0.45
    Activations Density 0.429%
    No Known Activations