Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12733
    Prev
    Next
    INDEX
    Explanations

    references to traditional Chinese medicine and cultural practices

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

    Code snippets and Chinese text

    np_acts-logits-general · gemini-2.0-flash

    Southern Song and Houston

    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
    parsedMessage
    -0.57
    
    -0.55
     disambiguazione
    -0.51
     statistiques
    -0.51
     nervously
    -0.50
    訝
    -0.47
     excitedly
    -0.47
    PageFactory
    -0.46
    dealloc
    -0.45
     incredibly
    -0.44
    POSITIVE LOGITS
    )");
    
    0.65
     ddelweddau
    0.64
     Efq
    0.64
    ]='\
    0.60
    \"");
    0.58
     Tropfen
    0.57
    ]));
    
    0.56
     Confucian
    0.56
     '"+
    0.56
     unterkunft
    0.56
    Activations Density 0.078%

    No Known Activations