© 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. 23-GEMMASCOPE-RES-16K
    6. 10137
    Prev
    Next
    INDEX
    Explanations

    the presence of public class declarations in the text

    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
    colgroup
    -0.36
     Ceramby
    -0.35
     cenar
    -0.35
     Expédié
    -0.34
     jestli
    -0.34
     թվական
    -0.34
     quizá
    -0.34
     dále
    -0.33
     lenker
    -0.33
     pře
    -0.33
    POSITIVE LOGITS
     AssemblyTitle
    0.62
    extAlignment
    0.61
     Episode
    0.57
    perties
    0.56
     Situation
    0.56
    acters
    0.55
    oustic
    0.54
     giác
    0.53
    setVerticalGroup
    0.53
     RSITY
    0.52
    Activations Density 0.035%

    No Known Activations