Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57074
    Prev
    Next
    INDEX
    Explanations

    issues related to power outages and electrical infrastructure failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.68
     autorytatywna
    -0.66
     nakalista
    -0.62
    rawDesc
    -0.61
     الاطلاع
    -0.60
    MLLoader
    -0.59
    #+#
    -0.58
    Controllo
    -0.57
    angliski
    -0.57
    uride
    -0.55
    POSITIVE LOGITS
     outage
    0.94
     outages
    0.92
     downtime
    0.64
     momentarily
    0.63
     overnight
    0.63
     kilowatt
    0.57
    tagHelperRunner
    0.57
     inconvenience
    0.56
     отклю
    0.55
     momentary
    0.55
    Activations Density 0.028%

    No Known Activations