© 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. 3-GEMMASCOPE-RES-16K
    6. 5720
    Prev
    Next
    INDEX
    Explanations

    phrases expressing excessiveness or extreme qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.78
    arote
    -0.76
    fillType
    -0.74
    )");
    
    -0.74
     */;
    -0.72
     vaisselle
    -0.72
    ucun
    -0.71
    APIView
    -0.71
    contentLoaded
    -0.71
     havaianas
    -0.70
    POSITIVE LOGITS
     too
    3.22
    too
    2.93
     Too
    2.86
    Too
    2.82
     TOO
    2.73
    TOO
    2.49
     demasiado
    1.83
     слишком
    1.79
     zbyt
    1.72
     terlalu
    1.70
    Activations Density 0.057%

    No Known Activations