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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2188
    Prev
    Next
    INDEX
    Explanations

    references to weddings and related events

    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
    findpost
    -0.95
    DockStyle
    -0.87
    ulties
    -0.83
     Wicidata
    -0.83
    NameInMap
    -0.79
    daß
    -0.78
    
    -0.77
    存于互联网档案馆
    -0.76
     AssemblyCulture
    -0.75
    woordig
    -0.75
    POSITIVE LOGITS
     wedding
    1.79
     Wedding
    1.60
    Wedding
    1.49
     weddings
    1.47
     WEDDING
    1.45
    wedding
    1.37
     Weddings
    1.17
     boda
    0.91
     helicopter
    0.82
     bodas
    0.80
    Activations Density 0.042%

    No Known Activations