© 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. 17-GEMMASCOPE-RES-16K
    11. 759
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related terms in legal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.67
    windowFixed
    -0.60
     vice
    -0.54
     be
    -0.54
    kuuta
    -0.53
     cost
    -0.51
     cap
    -0.51
     real
    -0.49
     text
    -0.48
     over
    -0.48
    POSITIVE LOGITS
     wikipagina
    0.71
    出版年
    0.70
    الدراسه
    0.68
    Personensuche
    0.68
    ंदीखरीदारी
    0.65
     cérami
    0.61
    RectangleBorder
    0.60
    তথ্যসূত্র
    0.59
    parsedMessage
    0.58
    bigliamento
    0.58
    Activations Density 0.139%

    No Known Activations