© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 51678
    Prev
    Next
    INDEX
    Explanations

    references to downtime and uptime in operational contexts

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

    time and activity states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunWith
    -0.44
     NSCoder
    -0.44
     croire
    -0.43
    ammlung
    -0.41
     Administrativna
    -0.41
    +:+
    -0.41
    tagHelper
    -0.40
    glä
    -0.40
    Sku
    -0.37
    förmig
    -0.37
    POSITIVE LOGITS
     downtime
    2.03
     uptime
    1.05
    uptime
    0.86
     idleness
    0.73
     outage
    0.69
     inactivity
    0.69
     outages
    0.68
     χρό
    0.67
     endTime
    0.66
     latency
    0.64
    Activations Density 0.001%

    No Known Activations