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. 13-GEMMASCOPE-RES-16K
    6. 12269
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to "of" and its occurrences in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.91
     raiſ
    -0.88
     itſelf
    -0.87
     himſelf
    -0.78
     becauſe
    -0.77
     ―――――
    -0.77
     Majefty
    -0.74
     uſed
    -0.73
     ་་
    -0.73
     dieß
    -0.73
    POSITIVE LOGITS
     de
    1.13
     De
    1.05
    Σε
    0.91
    indd
    0.89
     the
    0.88
     DE
    0.87
    De
    0.85
    بوابة
    0.80
    ]){
    
    0.79
    員の
    0.78
    Activations Density 0.025%

    No Known Activations