© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15618
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    -0.58
     zav
    -0.54
    RunAsync
    -0.51
     Carrington
    -0.50
    TextHelper
    -0.49
    [@
    -0.49
     Viel
    -0.48
     meet
    -0.48
    チップ
    -0.48
     않았
    -0.48
    POSITIVE LOGITS
    Tembelea
    0.97
     piú
    0.89
    
    0.86
     ostavi
    0.84
    ագրություններ
    0.84
    Архівовано
    0.81
     */
    0.77
     vnto
    0.75
     вікі
    0.71
     kasarigan
    0.69
    Activations Density 1.131%

    No Known Activations