© 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. 30-GEMMASCOPE-RES-16K
    11. 12388
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow structures in code

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

    Code snippets with "return", "=", or ":" tokens

    np_acts-logits-general · gemini-2.0-flash

    return assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.38
     людини
    -0.35
      
    -0.35
    n
    -0.35
    t
    -0.31
    a
    -0.28
    i
    -0.27
    不
    -0.27
     kolej
    -0.26
     set
    -0.26
    POSITIVE LOGITS
     autorytatywna
    1.06
     ویکی‌پدی
    0.88
    hoeddwyd
    0.85
    ➟
    0.85
    GOTREF
    0.85
     kasarigan
    0.84
    sizeCache
    0.84
    цездатний
    0.83
    出版年
    0.82
     defaultstate
    0.81
    Activations Density 0.213%

    No Known Activations