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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8153
    Prev
    Next
    INDEX
    Explanations

    legal roles and positions held by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.54
     rospy
    -0.52
    UrlResolution
    -0.50
    hynchus
    -0.48
     Guille
    -0.47
    createCanvas
    -0.46
     żyw
    -0.46
     rescat
    -0.45
    initializeApp
    -0.44
    belajaran
    -0.43
    POSITIVE LOGITS
     lawyers
    1.96
     Legal
    1.87
     legal
    1.86
     Lawyers
    1.80
    Legal
    1.79
     lawyer
    1.78
     attorneys
    1.78
     law
    1.75
    Law
    1.73
     Law
    1.72
    Activations Density 0.828%

    No Known Activations