© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14433
    Prev
    Next
    INDEX
    Explanations

    specific terms and references related to technical or scientific devices and methodologies

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

    abbreviations, codes, and identifiers

    np_acts-logits-general · gemini-2.0-flash

    specific nouns and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Datuak
    -0.61
    sizeCache
    -0.56
    Personendaten
    -0.55
     мәкал
    -0.54
     Comprometido
    -0.53
     Paglinawan
    -0.52
     autorytatywna
    -0.50
    Referanser
    -0.49
    ientôt
    -0.48
    -------------</
    -0.48
    POSITIVE LOGITS
    PAP
    0.53
     Legacy
    0.51
     PAP
    0.50
    WAU
    0.49
     ACE
    0.47
     CEC
    0.47
     charge
    0.46
     Ha
    0.46
     Manus
    0.46
     Fund
    0.46
    Activations Density 0.999%

    No Known Activations