© 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. 10484
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mark" as well as phrases indicating marking or highlighting actions

    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
    katapos
    -0.84
    bibinfo
    -0.74
    anjutnya
    -0.73
    氓
    -0.70
    tenham
    -0.69
     Auvergne
    -0.66
    קישורים
    -0.65
    onNext
    -0.64
    <thead>
    -0.63
    hlander
    -0.63
    POSITIVE LOGITS
     Mark
    2.57
     mark
    2.57
    Mark
    2.50
     marks
    2.41
     Marks
    2.41
    mark
    2.40
     MARK
    2.33
    MARK
    2.26
    Marks
    2.23
    marks
    2.21
    Activations Density 0.094%

    No Known Activations