© 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. 27-GEMMASCOPE-RES-16K
    11. 8948
    Prev
    Next
    INDEX
    Explanations

    suggestions about technology or improvements to systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gewöhnlich
    -0.62
     usually
    -0.50
     suele
    -0.48
     fallu
    -0.48
     suelen
    -0.46
     zahlreiche
    -0.46
     often
    -0.46
     leider
    -0.45
     genellikle
    -0.45
     zwykle
    -0.45
    POSITIVE LOGITS
     maybe
    0.82
    maybe
    0.71
     perhaps
    0.71
     magari
    0.70
     Maybe
    0.66
    Maybe
    0.65
    perhaps
    0.62
     somehow
    0.60
     ujednoznacz
    0.60
     Perhaps
    0.58
    Activations Density 0.970%

    No Known Activations