© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11908
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "en" in various forms and contexts

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

    French language text, particularly the word "en" and other common French words and phrases.

    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
    новниш
    -0.36
     bénévol
    -0.35
    ゚)
    -0.33
     nuage
    -0.31
    lihood
    -0.31
    fstream
    -0.31
     Robot
    -0.31
     Norvège
    -0.30
    asu
    -0.30
     pauvreté
    -0.30
    POSITIVE LOGITS
     CURLOPT
    0.62
    RegressionTest
    0.56
    libft
    0.52
    mybatisplus
    0.52
    cshtml
    0.50
    IContainer
    0.49
     minOccurs
    0.49
    DataAnnotations
    0.49
    rungsseite
    0.48
     restTemplate
    0.46
    Activations Density 0.060%

    No Known Activations