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. 20-GEMMASCOPE-RES-16K
    6. 1391
    Prev
    Next
    INDEX
    Explanations

    references to programming and software-related concepts

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

    Code, paths, and programming terms

    np_acts-logits-general · gemini-2.0-flash

    of those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.65
      
    -0.58
         
    -0.57
       
    -0.57
    SourceChecksum
    -0.57
           
    -0.56
    principalTable
    -0.56
     архивлан
    -0.56
     easter
    -0.55
    TagMode
    -0.54
    POSITIVE LOGITS
    JvmStatic
    0.62
    Demikian
    0.60
     tslint
    0.57
    WriteTagHelper
    0.56
    endpush
    0.55
    seamnă
    0.55
    というわけで
    0.54
    imanapun
    0.54
     "$@"
    0.53
     ziren
    0.53
    Activations Density 0.177%

    No Known Activations