© 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. 27-GEMMASCOPE-RES-16K
    11. 12106
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court proceedings and judicial outcomes

    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
     yourselves
    -0.55
     ourselves
    -0.54
    她們
    -0.49
    JvmStatic
    -0.47
     करती
    -0.45
     själva
    -0.44
    它們
    -0.44
     juntas
    -0.44
     our
    -0.43
    她们
    -0.43
    POSITIVE LOGITS
     his
    2.31
     himself
    2.00
    himself
    1.77
    his
    1.68
     그의
    1.58
     he
    1.55
    彼の
    1.54
    他的
    1.52
    彼は
    1.48
     seiner
    1.46
    Activations Density 2.886%

    No Known Activations