© 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. 5-GEMMASCOPE-RES-16K
    11. 7235
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.85
     myſelf
    -0.73
     AssemblyCulture
    -0.72
    troppo
    -0.70
    RunAsync
    -0.68
     Houſe
    -0.67
     chi̍t
    -0.67
     Theſe
    -0.67
    Numerology
    -0.67
     houſe
    -0.67
    POSITIVE LOGITS
     ostavi
    0.56
     cas
    0.53
    googleapis
    0.51
    QRCode
    0.50
     cho
    0.50
     ked
    0.50
     insp
    0.49
    Queryable
    0.48
    éné
    0.47
    wal
    0.46
    Activations Density 0.560%

    No Known Activations