© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structural components within code

    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
    States
    -0.96
    STATES
    -0.86
     STATES
    -0.83
     myſelf
    -0.83
     faſt
    -0.82
    thâu
    -0.79
    states
    -0.79
    AnchorStyles
    -0.79
     fubject
    -0.77
     States
    -0.75
    POSITIVE LOGITS
     state
    0.47
     stated
    0.47
     sta
    0.47
     tat
    0.45
     stat
    0.40
     statt
    0.38
     государ
    0.34
    tat
    0.31
     ста
    0.30
     State
    0.29
    Activations Density 0.310%

    No Known Activations