© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90959
    Prev
    Next
    INDEX
    Explanations

    boolean expressions and control flow structures in programming language code

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

    infinite loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.85
     فريبيس
    -0.78
    ſelben
    -0.77
     deſſen
    -0.77
    ſſung
    -0.76
    rungsseite
    -0.76
     متعلقه
    -0.75
    
    -0.75
    citroën
    -0.75
    iſche
    -0.75
    POSITIVE LOGITS
     (;;)
    0.45
     (;;
    0.45
    (;;)
    0.33
    expandindo
    0.28
    GEBURTSDATUM
    0.27
    e
    0.25
    beginPath
    0.20
     frem
    0.19
    Input
    0.19
    readystatechange
    0.19
    Activations Density 0.001%

    No Known Activations