© 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. 0-GEMMASCOPE-RES-16K
    11. 8180
    Prev
    Next
    INDEX
    Explanations

    references to chapters and numerical ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tunggal
    -0.61
    horabuena
    -0.50
     glú
    -0.48
     verkau
    -0.47
     alimentaria
    -0.47
     mutlu
    -0.47
     muerta
    -0.47
    destroyAll
    -0.46
     poffible
    -0.46
    ArrowToggle
    -0.46
    POSITIVE LOGITS
     effect
    0.67
     chapter
    0.65
     Chapters
    0.64
     chase
    0.61
     Chapter
    0.59
     mercy
    0.57
     chap
    0.57
    Chapters
    0.56
     Chap
    0.56
     genre
    0.55
    Activations Density 0.298%

    No Known Activations