© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9441
    Prev
    Next
    INDEX
    Explanations

    numerical values and variable names in code-related contexts

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

    Variables or parameters in code/formulas

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.88
    expandindo
    -0.84
    IntoConstraints
    -0.81
    المناصب
    -0.80
     informée
    -0.79
     transfieras
    -0.77
     @"/
    -0.77
     kasarigan
    -0.77
    <unused52>
    -0.75
     surla
    -0.75
    POSITIVE LOGITS
     fő
    0.34
    .”
    0.31
     keduanya
    0.31
    <eos>
    0.29
    ↵↵↵
    0.28
     Вікіпе
    0.28
     båda
    0.28
     jį
    0.28
     eşofman
    0.28
     declaración
    0.27
    Activations Density 0.626%

    No Known Activations