© 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. 4-GEMMASCOPE-RES-16K
    11. 2104
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases indicating the addition of information or emphasis in scientific discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     help
    -0.72
    reciate
    -0.71
    RectangleBorder
    -0.67
     Stil
    -0.67
    /*
    -0.67
     Help
    -0.66
    addPreferredGap
    -0.65
     Sorry
    -0.64
     Bitte
    -0.64
     Breen
    -0.63
    POSITIVE LOGITS
    Moreover
    1.63
     Moreover
    1.56
     moreover
    1.56
    Furthermore
    1.42
     Furthermore
    1.38
     furthermore
    1.36
    Asimismo
    0.95
     Asimismo
    0.86
     Inoltre
    0.86
    Inoltre
    0.86
    Activations Density 0.173%

    No Known Activations