© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35507
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in programming code

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

    application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hésite
    -0.60
     daños
    -0.50
     Vorschriften
    -0.49
    ltä
    -0.49
     tää
    -0.48
     jueces
    -0.47
     mécanisme
    -0.46
     Garantía
    -0.46
     muebles
    -0.45
     eléctrico
    -0.44
    POSITIVE LOGITS
     application
    1.28
     Application
    1.22
    application
    1.20
    Application
    1.16
     applications
    1.06
     Applications
    1.03
     APPLICATION
    0.99
    Applications
    0.94
    APPLICATION
    0.92
    applications
    0.91
    Activations Density 0.024%

    No Known Activations