© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 1329
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate the discovery or revelation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.88
     U
    -0.79
     I
    -0.73
     kaynağından
    -0.67
      
    -0.66
     colspan
    -0.66
     i
    -0.65
     or
    -0.65
     D
    -0.65
    ymce
    -0.64
    POSITIVE LOGITS
     Reveal
    1.94
    Reveal
    1.72
     reveal
    1.72
     Reveals
    1.69
    reveal
    1.65
     reveals
    1.65
     revealed
    1.62
     Revealed
    1.61
     disclosed
    1.57
     revealing
    1.55
    Activations Density 0.056%

    No Known Activations