© 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. 12-GEMMASCOPE-RES-16K
    11. 13745
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to specialties and expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scénario
    -0.57
    StoryboardSegue
    -0.51
    autique
    -0.49
     Muss
    -0.49
    uspiel
    -0.49
    ngoing
    -0.48
     estekak
    -0.48
    ьажоргаш
    -0.48
    󠁴
    -0.48
    Muss
    -0.47
    POSITIVE LOGITS
     specialize
    1.05
     specialise
    1.00
     specializes
    1.00
     specialises
    0.97
     specialization
    0.94
     specializing
    0.93
     specialty
    0.91
     specialising
    0.88
     specialized
    0.88
     specialised
    0.86
    Activations Density 0.267%

    No Known Activations