© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5377
    Prev
    Next
    INDEX
    Explanations

    French-specific grammatical structures and indicators of identity or position

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

    after French articles (un, au, du, nouvel)

    np_acts-logits-general · gemini-2.0-flash

    determiner followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.95
     Majefty
    -0.71
     senador
    -0.66
     jäsen
    -0.64
     évêque
    -0.64
     monasteries
    -0.64
     courts
    -0.63
     kvinnor
    -0.62
     Cornelia
    -0.62
    ///</
    -0.62
    POSITIVE LOGITS
     disc
    0.46
     prom
    0.41
     j
    0.41
     loc
    0.40
     pion
    0.40
    évaluateur
    0.40
     milit
    0.39
    urat
    0.38
     Pages
    0.38
    Milit
    0.38
    Activations Density 0.052%

    No Known Activations