© 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. 24-GEMMASCOPE-RES-16K
    11. 5441
    Prev
    Next
    INDEX
    Explanations

    parentheses and related syntax structures in code

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

    Code, parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    code assertions

    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
    adaptiveStyles
    -0.79
    Билгалдахарш
    -0.78
     Paglinawan
    -0.72
    jspb
    -0.71
    uxxxx
    -0.70
    OGND
    -0.69
    Portály
    -0.68
     otomatig
    -0.68
    awtextra
    -0.67
    下载附件
    -0.66
    POSITIVE LOGITS
     ferner
    0.41
     húmedo
    0.39
     penas
    0.37
     Autorin
    0.37
     extranjera
    0.35
     gruesa
    0.34
    Major
    0.34
     testigos
    0.33
    Principales
    0.33
     algas
    0.33
    Activations Density 0.245%

    No Known Activations