© 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. 10217
    Prev
    Next
    INDEX
    Explanations

    references to digital content and technology-related experiences

    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
     finalmente
    -0.50
     inaugural
    -0.45
     يتيمه
    -0.44
     erstmals
    -0.43
     will
    -0.43
     Initially
    -0.42
     initial
    -0.42
     inicialmente
    -0.41
    reszcie
    -0.40
     finally
    -0.40
    POSITIVE LOGITS
     sometimes
    1.10
     occasionally
    1.09
    sometimes
    1.02
    Occasionally
    1.00
     Occasionally
    1.00
     regularly
    0.99
     often
    0.96
     whenever
    0.95
     routinely
    0.94
     oftentimes
    0.94
    Activations Density 0.761%

    No Known Activations