© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9059
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "non" or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horaire
    -0.73
     doulou
    -0.70
     vettor
    -0.69
     héri
    -0.69
     urbain
    -0.69
     littéraire
    -0.68
     scuro
    -0.67
     rése
    -0.66
    DockStyle
    -0.66
     rumahnya
    -0.65
    POSITIVE LOGITS
     non
    3.13
    Non
    2.99
     Non
    2.95
    non
    2.89
     NON
    2.71
    NON
    2.49
    非
    2.30
     nons
    1.87
     非
    1.86
     Nons
    1.80
    Activations Density 0.076%

    No Known Activations