© 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. 11728
    Prev
    Next
    INDEX
    Explanations

    mentions of medical devices, emergency response terminology, and karaoke-related keywords

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

    words related to karaoke and singing equipment or activities.

    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
     kasarigan
    -0.82
    httphttps
    -0.77
     Chwiliwch
    -0.75
     Taktlose
    -0.72
     وتسجيلات
    -0.69
     consultato
    -0.66
    Билгалдахарш
    -0.65
     otomatig
    -0.65
     disambiguazione
    -0.63
    Slf
    -0.62
    POSITIVE LOGITS
     Martel
    0.47
     Wyman
    0.43
    fillRect
    0.43
     éc
    0.40
    Formik
    0.40
     gió
    0.40
     dormitórios
    0.39
     Kitch
    0.39
    DecimalFormat
    0.38
    Fußball
    0.38
    Activations Density 2.777%

    No Known Activations