© 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. 18-GEMMASCOPE-RES-16K
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming terms and functions, especially those involving object manipulation and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Non-English words or phrases

    np_acts-logits-general · gemini-2.0-flash

    you can delete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.85
    vrigt
    -0.76
     πως
    -0.75
     illetve
    -0.70
     όμως
    -0.68
     hiszen
    -0.66
    -
    -0.66
     tzw
    -0.66
     sämtliche
    -0.66
     chaine
    -0.64
    POSITIVE LOGITS
     XNUMX
    1.88
     itſelf
    1.72
     myſelf
    1.67
    NUMX
    1.47
     Efq
    1.44
     Theſe
    1.39
     becauſe
    1.39
     Monfieur
    1.37
     ſtate
    1.37
     himſelf
    1.36
    Activations Density 0.096%

    No Known Activations