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. 15-GEMMASCOPE-RES-16K
    6. 12643
    Prev
    Next
    INDEX
    Explanations

    structured data or numerical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İstinadlar
    -0.57
     Rata
    -0.52
     Walkover
    -0.51
     STUART
    -0.49
    erv
    -0.49
    Personensuche
    -0.48
    euvre
    -0.48
     Sty
    -0.48
     Balo
    -0.48
     #:
    -0.48
    POSITIVE LOGITS
    viewDidLoad
    0.76
    Последние
    0.69
    principalColumn
    0.67
     négatif
    0.62
    UrlResolution
    0.62
     initComponents
    0.61
     marqué
    0.59
    ViewFeatures
    0.58
     actionMode
    0.57
     mourir
    0.57
    Activations Density 0.410%

    No Known Activations