© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14874
    Prev
    Next
    INDEX
    Explanations

    references to logging frameworks and related implementations in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.78
     '\\;'
    -0.77
    хьтан
    -0.73
    GEBURTSDATUM
    -0.73
     Anſ
    -0.68
     Chwiliwch
    -0.67
    AddTagHelper
    -0.66
     cauſe
    -0.65
     anſ
    -0.65
     OMITBAD
    -0.64
    POSITIVE LOGITS
    getLogger
    1.00
    LoggerFactory
    0.96
    Slf
    0.90
    Logger
    0.79
    logger
    0.70
     Logger
    0.69
    LOGGER
    0.61
     logger
    0.59
    LogFactory
    0.58
     ILogger
    0.56
    Activations Density 0.075%

    No Known Activations