© 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. 23-GEMMASCOPE-RES-16K
    11. 1504
    Prev
    Next
    INDEX
    Explanations

    references to support and funding for content creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classnames
    -0.59
    tial
    -0.54
     Result
    -0.49
     makeStyles
    -0.49
    olympic
    -0.48
    cian
    -0.48
    Highlights
    -0.48
     Notably
    -0.47
    marginHorizontal
    -0.47
     Results
    -0.47
    POSITIVE LOGITS
     pendukung
    0.35
     pisang
    0.34
     noDo
    0.32
    endroit
    0.31
    AnchorTagHelper
    0.31
     bénévol
    0.31
     támogat
    0.31
     Comprometido
    0.31
    awsze
    0.30
     näin
    0.29
    Activations Density 0.210%

    No Known Activations