© 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. 37-GEMMASCOPE-RES-16K
    11. 3737
    Prev
    Next
    INDEX
    Explanations

    assertions of "good news" or positive outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnore
    -0.41
    Tembelea
    -0.38
     klaar
    -0.36
     Superhosts
    -0.36
    ronpa
    -0.36
    EndTag
    -0.35
    fjspx
    -0.35
    formik
    -0.35
     Ante
    -0.35
     Infra
    -0.35
    POSITIVE LOGITS
     news
    3.67
    news
    2.94
     News
    2.81
    News
    2.72
     NEWS
    2.67
    NEWS
    2.45
     noticias
    2.42
     berita
    2.31
     noticia
    2.30
     nieuws
    2.23
    Activations Density 0.678%

    No Known Activations