© 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. 1-GEMMASCOPE-RES-16K
    6. 13084
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    binant
    -0.62
    Recall
    -0.61
    newArrayList
    -0.61
    
    -0.60
     Recall
    -0.59
     faune
    -0.58
     المعيارى
    -0.57
    %">
    -0.56
     Loeb
    -0.56
     indeb
    -0.55
    POSITIVE LOGITS
     prize
    0.91
     percentage
    0.90
    percentage
    0.88
     prizes
    0.88
     MainAxisSize
    0.84
     Percentage
    0.82
     percentages
    0.81
     PRIZE
    0.79
     Prizes
    0.77
     Prize
    0.73
    Activations Density 0.072%

    No Known Activations