© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11542
    Prev
    Next
    INDEX
    Explanations

    various forms and conventions of references to 'e' and 'E', possibly relating to electronic or coding contexts

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

    abbreviated forms like "e.g." at the beginning of examples or explanations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the letter "e" at the beginning of abbreviations or acronyms (e.g., "e-commerce", "e-ink").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    offrir
    -0.47
     Harz
    -0.44
    empêcher
    -0.44
     obispo
    -0.43
    atmosphère
    -0.40
     Perspek
    -0.40
    atteindre
    -0.40
    hygiène
    -0.39
    dowa
    -0.39
     Valentín
    -0.39
    POSITIVE LOGITS
    IndentedString
    0.65
    parsedMessage
    0.59
     GenerationType
    0.56
    GEBURTSDATUM
    0.54
     E
    0.52
    oe
    0.51
    oke
    0.50
     e
    0.49
    getE
    0.49
    ee
    0.48
    Activations Density 0.341%

    No Known Activations