© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9930
    Prev
    Next
    INDEX
    Explanations

    terms related to processes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catawiki
    -0.65
    doir
    -0.61
     Orto
    -0.61
     gepubliceerd
    -0.59
     ++)
    -0.58
    BeginContext
    -0.58
    ::~
    -0.58
    
    -0.58
     fidu
    -0.58
     архивлан
    -0.57
    POSITIVE LOGITS
    Process
    1.04
    process
    1.01
     Process
    0.96
     process
    0.86
    PROCESS
    0.86
    Processes
    0.80
     Processes
    0.80
     PROCESS
    0.76
     processes
    0.75
    processes
    0.74
    Activations Density 0.127%

    No Known Activations