© 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. 39-GEMMASCOPE-RES-16K
    11. 866
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and terms related to evidence and court procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خدم
    -0.43
    tský
    -0.42
    ciec
    -0.41
    giaan
    -0.40
     asistir
    -0.39
    Jaunes
    -0.39
     Schäfer
    -0.39
    záll
    -0.39
     ellas
    -0.39
    浴び
    -0.39
    POSITIVE LOGITS
     noDo
    0.57
     ujednoznacz
    0.55
    endpush
    0.51
    CloseOperation
    0.50
    +#+
    0.49
    Välislingid
    0.48
     consultato
    0.48
     chi̍t
    0.47
     通販
    0.47
    NUMX
    0.47
    Activations Density 1.568%

    No Known Activations