© 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. 16-GEMMASCOPE-RES-16K
    6. 14269
    Prev
    Next
    INDEX
    Explanations

    sections of text that are entirely void of any meaningful content or activations

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

    Word after a period

    np_acts-logits-general · gemini-2.0-flash

    often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.59
    __':
    -0.52
    fillna
    -0.52
     materially
    -0.51
    __':
    
    -0.48
    المشاركات
    -0.48
    ➌
    -0.48
     الدولى
    -0.48
    كامل
    -0.48
    testify
    -0.47
    POSITIVE LOGITS
     Often
    0.83
    Often
    0.82
     often
    0.78
     wondering
    0.75
     kadang
    0.74
    often
    0.73
     oftentimes
    0.72
    Wondering
    0.72
     spesso
    0.72
     understandably
    0.70
    Activations Density 0.175%

    No Known Activations