© 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. 20-GEMMASCOPE-RES-16K
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory terms or documents

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

    completeness or totality

    np_acts-logits-general · gemini-2.0-flash

    complete, entirely, fully

    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
    enumi
    -0.82
     مشين
    -0.75
    Бахар
    -0.68
    msgTypes
    -0.67
     autorytatywna
    -0.65
    ArrowToggle
    -0.65
     bezeichneter
    -0.64
     nakalista
    -0.60
     Waray
    -0.60
    TypedDataSet
    -0.58
    POSITIVE LOGITS
     fully
    2.21
     completely
    2.20
     full
    2.18
     complete
    1.97
     completo
    1.93
     entirely
    1.91
     Completely
    1.86
     FULL
    1.85
     totally
    1.84
     complet
    1.83
    Activations Density 0.481%

    No Known Activations