© 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. 40-GEMMASCOPE-RES-16K
    11. 1213
    Prev
    Next
    INDEX
    Explanations

    elements related to data handling and reporting in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.63
     صوتيه
    -0.52
     שוליים
    -0.52
    parsedMessage
    -0.45
    Бележки
    -0.43
     AssemblyCulture
    -0.41
    esModule
    -0.41
     PSR
    -0.40
     htons
    -0.40
    Източници
    -0.40
    POSITIVE LOGITS
     report
    0.73
     drill
    0.69
     query
    0.66
     Report
    0.65
     queries
    0.64
     Drill
    0.63
     pivot
    0.63
     Pivot
    0.62
     slicer
    0.61
    drill
    0.59
    Activations Density 0.718%

    No Known Activations