© 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. 30-GEMMASCOPE-RES-16K
    6. 10555
    Prev
    Next
    INDEX
    Explanations

    references to articles or sections within a publication

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

    newspapers or columns

    np_acts-logits-general · gemini-2.0-flash

    newspaper articles and columns

    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
    CHAPTER
    -0.48
     CHAPTER
    -0.47
     chapter
    -0.47
     Kön
    -0.47
    Chapter
    -0.43
     Chapter
    -0.41
    دانلود
    -0.40
     kurtka
    -0.40
     chapters
    -0.38
    chapter
    -0.38
    POSITIVE LOGITS
     newspaper
    0.93
     Newspaper
    0.91
    newspaper
    0.81
    Newspaper
    0.81
     Newspapers
    0.76
     newspapers
    0.75
     columnist
    0.71
     Circulation
    0.66
     Editorial
    0.66
     column
    0.64
    Activations Density 0.393%

    No Known Activations