© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7767
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance monitoring and reporting systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.90
     للمعارف
    -0.89
     صوتيه
    -0.76
    Geplaatst
    -0.74
    tagHelperRunner
    -0.74
    WriteBarrier
    -0.73
     nahilalakip
    -0.69
    BufferException
    -0.68
    ExtendWith
    -0.64
    
    -0.63
    POSITIVE LOGITS
     metrics
    0.95
     report
    0.88
     reporting
    0.87
     statistics
    0.86
     measurement
    0.85
     measuring
    0.83
     data
    0.82
     metric
    0.80
     statistical
    0.80
     measure
    0.80
    Activations Density 0.999%

    No Known Activations