© 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. 13-GEMMASCOPE-RES-16K
    11. 7378
    Prev
    Next
    INDEX
    Explanations

    references to news and updates, particularly those that are reports or bulletins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corbu
    -0.50
     Salter
    -0.47
    itec
    -0.45
    batore
    -0.44
    metic
    -0.44
     Racine
    -0.44
    bingen
    -0.44
    ölker
    -0.43
    bondale
    -0.42
    per
    -0.41
    POSITIVE LOGITS
     news
    1.70
     News
    1.57
     NEWS
    1.51
    News
    1.46
    news
    1.45
    NEWS
    1.28
     noticia
    1.20
     noticias
    1.11
     notícia
    1.08
     berita
    1.06
    Activations Density 0.087%

    No Known Activations