© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11277
    Prev
    Next
    INDEX
    Explanations

    terms related to application management and monitoring features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.43
     CanadaChoose
    -0.41
    BackStack
    -0.40
     doInBackground
    -0.39
     Pil
    -0.39
    RectangleBorder
    -0.39
    Rip
    -0.38
     safe
    -0.37
    AccessorTable
    -0.37
    Bissau
    -0.37
    POSITIVE LOGITS
     metrics
    0.77
     Metrics
    0.74
     metric
    0.71
     Metric
    0.71
     monitoring
    0.66
     Prometheus
    0.65
     Alert
    0.63
    报警
    0.62
    Metric
    0.60
     alarm
    0.60
    Activations Density 0.475%

    No Known Activations