© 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. 4755
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and court proceedings

    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
    şekkür
    -0.45
     gesprochen
    -0.38
    Address
    -0.38
     confirme
    -0.38
    confirmation
    -0.37
     confirma
    -0.37
    aarrggbb
    -0.35
    ativement
    -0.35
    szönöm
    -0.35
     confirmó
    -0.35
    POSITIVE LOGITS
     argue
    1.66
     argued
    1.47
     argues
    1.38
     arguing
    1.37
     claim
    1.34
     contended
    1.27
     argument
    1.27
     contends
    1.26
     contend
    1.26
     contention
    1.24
    Activations Density 0.862%

    No Known Activations