Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4429
    Prev
    Next
    INDEX
    Explanations

    terms related to "non" or "non-standard" classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     italienne
    -0.77
     ulang
    -0.75
     scuro
    -0.73
     Vikipedi
    -0.71
     recib
    -0.71
     innamor
    -0.70
    myModal
    -0.69
     imprimée
    -0.69
     remé
    -0.67
     sguardo
    -0.66
    POSITIVE LOGITS
     non
    1.50
     Non
    1.45
     NON
    1.44
    Non
    1.39
    non
    1.30
    非
    1.25
     nong
    1.19
     nons
    1.17
    NON
    1.16
     Nons
    1.12
    Activations Density 0.098%

    No Known Activations