© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6682
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax in a code-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.09
     Monfieur
    -1.09
     myſelf
    -1.06
     crdi
    -1.04
     itſelf
    -1.00
     Reſ
    -0.98
     Theſe
    -0.96
     diſt
    -0.93
     whoſe
    -0.93
     pleaſure
    -0.92
    POSITIVE LOGITS
     if
    0.72
    if
    0.66
     all
    0.55
     (
    0.52
     ne
    0.52
     Rad
    0.50
     !
    0.49
     ny
    0.49
    nes
    0.48
     sp
    0.48
    Activations Density 0.035%

    No Known Activations