© 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. 30-GEMMASCOPE-RES-16K
    11. 10870
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines and community moderation practices

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

    Wikipedia categories and file information

    np_acts-logits-general · gemini-2.0-flash

    wikipedia entries and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Branchen
    -0.34
     compañías
    -0.34
     Compañ
    -0.29
     láser
    -0.28
     escuchado
    -0.28
    tür
    -0.28
     Strecke
    -0.28
     marketing
    -0.28
     boucle
    -0.28
     companies
    -0.28
    POSITIVE LOGITS
     Wikipedia
    1.02
     wiki
    0.94
     wik
    0.90
     wikipedia
    0.89
     Wikiped
    0.88
     Wikipédia
    0.87
    wikimedia
    0.87
     Wiki
    0.87
     Wikimedia
    0.87
    Wikipedia
    0.83
    Activations Density 0.431%

    No Known Activations