© 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. 8-GEMMASCOPE-RES-16K
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    sequences that involve specific patterns in text formatting or structuring elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.25
    InjectAttribute
    -1.23
    Vidite
    -1.20
     Majefty
    -1.13
    
    -1.07
     nahilalakip
    -1.06
     Infórmanos
    -1.05
     raiſ
    -1.04
    webElementXpaths
    -1.03
     Numerade
    -1.02
    POSITIVE LOGITS
     
    0.86
      
    0.76
     '
    0.63
     is
    0.59
     S
    0.59
     start
    0.58
       
    0.57
     a
    0.57
     the
    0.56
     main
    0.54
    Activations Density 0.056%

    No Known Activations