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. 19-GEMMASCOPE-RES-16K
    6. 2230
    Prev
    Next
    INDEX
    Explanations

    specific instances and mentions of events or significant occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intenant
    -0.69
     étrang
    -0.68
     للاسماء
    -0.63
     démocr
    -0.63
     mauva
    -0.61
     provence
    -0.61
     malheure
    -0.61
     étrangère
    -0.60
     regionales
    -0.59
     nettoy
    -0.59
    POSITIVE LOGITS
     obtained
    0.80
     main
    0.75
    obtained
    0.72
     «
    0.70
     peculiarity
    0.66
     mentioned
    0.65
     analysed
    0.65
     own
    0.64
     so
    0.62
     whole
    0.60
    Activations Density 0.513%

    No Known Activations