© 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. 31-GEMMASCOPE-RES-16K
    11. 8746
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to contracts and their enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal contract terms and provisions, particularly those related to damages, obligations, and agreement enforceability.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.37
     قب
    -0.35
     skå
    -0.29
     заключа
    -0.29
     yến
    -0.27
     concluded
    -0.27
    träger
    -0.27
    gorm
    -0.26
     boy
    -0.26
    oceros
    -0.26
    POSITIVE LOGITS
     provisions
    1.73
     provision
    1.59
     clauses
    1.59
     clause
    1.59
    provision
    1.55
     Provisions
    1.47
     Provision
    1.35
     PROVISIONS
    1.34
    Provision
    1.30
     Clause
    1.27
    Activations Density 0.995%

    No Known Activations