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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7340
    Prev
    Next
    INDEX
    Explanations

    technical terms and commands related to script execution and cron jobs

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

    Code execution, scheduling, and automation

    np_acts-logits-general · gemini-2.0-flash

    cron jobs and automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.39
    InputBorder
    -0.36
     geçi
    -0.31
    jface
    -0.31
    addGap
    -0.30
     maisha
    -0.29
    DockStyle
    -0.29
    hyrchwyd
    -0.28
     transición
    -0.28
     prakti
    -0.28
    POSITIVE LOGITS
     process
    0.75
     batch
    0.74
     jobs
    0.74
     task
    0.72
     run
    0.71
     tasks
    0.70
     automation
    0.69
     queued
    0.66
     scheduled
    0.65
     queue
    0.65
    Activations Density 0.887%

    No Known Activations