© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 6994
    Prev
    Next
    INDEX
    Explanations

    data related to case management and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſcher
    -0.73
    ésultats
    -0.69
     queſta
    -0.68
     informée
    -0.68
    Spolja
    -0.67
     otomatig
    -0.67
    fromnode
    -0.66
    iſen
    -0.66
    <pad>
    -0.65
     verſch
    -0.65
    POSITIVE LOGITS
     two
    0.34
    d
    0.33
     operating
    0.31
    a
    0.30
    subsubsection
    0.29
     AG
    0.28
     pla
    0.28
    mn
    0.28
    ж
    0.28
     Mills
    0.27
    Activations Density 0.678%

    No Known Activations