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. 5-GEMMASCOPE-RES-16K
    6. 10516
    Prev
    Next
    INDEX
    Explanations

    the word "This" and its variations, indicating the presence of references or descriptions in the text

    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
     NSCoder
    -0.94
     endregion
    -0.94
     Cfr
    -0.91
    ArrowToggle
    -0.88
     Efq
    -0.87
    المناصب
    -0.87
     _("
    -0.86
    aarrggbb
    -0.86
    \}\\
    -0.85
    
    -0.85
    POSITIVE LOGITS
    This
    1.01
    this
    1.00
     This
    0.97
     this
    0.79
    THIS
    0.76
     THIS
    0.75
    本
    0.61
     esta
    0.59
     este
    0.56
     هذا
    0.56
    Activations Density 0.307%

    No Known Activations