© 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. 2779
    Prev
    Next
    INDEX
    Explanations

    references to individuals with specific academic or professional titles

    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
    Rüyada
    -0.66
     teor
    -0.45
    édrale
    -0.44
    خم
    -0.43
     могли
    -0.40
     soll
    -0.40
    商品説明
    -0.39
     contener
    -0.38
    TAWA
    -0.38
    tryk
    -0.38
    POSITIVE LOGITS
     saites
    0.82
    出版年
    0.81
    Geplaatst
    0.75
    paravant
    0.69
     BoxDecoration
    0.68
     nakalista
    0.67
    الإنجليزية
    0.66
     viewType
    0.65
     defaultstate
    0.65
     InputDecoration
    0.64
    Activations Density 0.554%

    No Known Activations