© 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. 557
    Prev
    Next
    INDEX
    Explanations

    references to organized initiatives and programs relating to health, science, and community service

    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
     kyllä
    -0.47
     незавершена
    -0.44
     quedando
    -0.44
     verliert
    -0.43
     hinting
    -0.43
     deixando
    -0.42
    Geplaatst
    -0.42
     mentioning
    -0.41
    parsedMessage
    -0.40
     kaarangay
    -0.40
    POSITIVE LOGITS
     aims
    1.38
     seeks
    1.27
     aim
    1.27
     seek
    1.12
    aim
    1.03
     aimed
    1.00
    Aims
    0.95
     Aims
    0.94
     aiming
    0.93
     sought
    0.91
    Activations Density 0.569%

    No Known Activations