© 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. 7-GEMMASCOPE-RES-16K
    11. 6890
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to marking or labeling items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    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
    -0.78
    tenham
    -0.75
     Montagu
    -0.73
    satunya
    -0.70
    氓
    -0.70
    edicated
    -0.69
    <tbody>
    -0.68
    anjutnya
    -0.67
    bibinfo
    -0.66
     Gauthier
    -0.65
    POSITIVE LOGITS
     Marks
    1.91
     marks
    1.75
     Mark
    1.71
    Marks
    1.70
     mark
    1.69
     MARKS
    1.67
     MARK
    1.65
    Mark
    1.64
    marks
    1.60
    mark
    1.56
    Activations Density 0.101%

    No Known Activations