© 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. 37-GEMMASCOPE-RES-16K
    11. 3352
    Prev
    Next
    INDEX
    Explanations

    references to working and related activities or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     work
    -1.52
     working
    -1.38
     worked
    -1.36
    work
    -1.23
     works
    -1.23
    working
    -1.18
    工作
    -1.17
     WORK
    -1.17
     workings
    -1.16
     trabajan
    -1.11
    POSITIVE LOGITS
    HasAnnotation
    0.62
    parsedMessage
    0.61
    EDEFAULT
    0.60
     behalf
    0.60
     pleaſure
    0.58
     CreateTagHelper
    0.56
     tirelessly
    0.55
    WriteTagHelper
    0.54
    msgTypes
    0.53
     relâche
    0.52
    Activations Density 0.291%

    No Known Activations