© 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. 23-GEMMASCOPE-RES-16K
    11. 12864
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and symbols related to coding or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.64
    SBATCH
    -0.59
    Brother
    -0.54
     Eighteen
    -0.54
     XVIII
    -0.52
     Brother
    -0.50
     resourceCulture
    -0.49
     Twelve
    -0.48
    brother
    -0.48
    EndContext
    -0.48
    POSITIVE LOGITS
    5
    2.01
     five
    1.74
     fifth
    1.73
     Fifth
    1.67
     Five
    1.62
     FIVE
    1.60
    five
    1.54
    Fifth
    1.49
    ５
    1.46
     cinco
    1.45
    Activations Density 1.804%

    No Known Activations