© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8596
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the color "red"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shakspeare
    -0.79
     fubject
    -0.77
    下载附件
    -0.77
     Diſ
    -0.75
     ſever
    -0.73
     preſent
    -0.72
     themſelves
    -0.72
     Cæsar
    -0.71
     Majefty
    -0.70
     houſe
    -0.69
    POSITIVE LOGITS
     red
    1.37
    red
    1.28
     Red
    1.23
    Red
    1.21
    RED
    1.04
    红
    0.95
     RED
    0.92
    紅
    0.84
    ंदीखरीदारी
    0.79
     红
    0.76
    Activations Density 0.100%

    No Known Activations