© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    technical terms and patterns related to process management in programming

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

    "process" or "processes"

    np_acts-logits-general · gemini-2.0-flash

    process and pid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.46
     bricolaje
    -0.40
    ftagPool
    -0.38
     committee
    -0.37
     cómics
    -0.35
    httphttps
    -0.34
     mobilya
    -0.34
     lieux
    -0.34
     Committee
    -0.34
    iség
    -0.34
    POSITIVE LOGITS
     Processes
    0.81
     Process
    0.80
     processes
    0.80
     process
    0.79
     pid
    0.75
    Process
    0.75
    Processes
    0.73
    进程
    0.70
     PID
    0.69
     processus
    0.69
    Activations Density 0.787%

    No Known Activations