© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14714
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific studies

    np_acts-logits-general · gemini-2.0-flash

    studies and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.72
    kloped
    -0.65
    WebpackPlugin
    -0.64
    EndInit
    -0.63
    withIdentifier
    -0.62
    djangoproject
    -0.62
    CloseOperation
    -0.60
     MainAxisSize
    -0.60
    fastjson
    -0.58
    </tfoot>
    -0.57
    POSITIVE LOGITS
     conducted
    1.17
     examining
    0.88
    conducted
    0.86
     Conducted
    0.81
     involving
    0.79
     evaluating
    0.78
     uitgevoerd
    0.78
     focused
    0.78
     focusing
    0.77
     undertaken
    0.76
    Activations Density 0.747%

    No Known Activations