© 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. 2-GEMMASCOPE-RES-16K
    11. 16233
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Everybody
    -0.90
     Everybody
    -0.87
     everybody
    -0.83
     big
    -0.82
     things
    -0.78
     people
    -0.78
    Somebody
    -0.77
     really
    -0.77
    Kalau
    -0.77
     Maybe
    -0.76
    POSITIVE LOGITS
     tevens
    1.20
     می‌باشد
    1.16
     nonché
    1.16
     thereof
    1.10
     herein
    1.08
     및
    1.06
     있으며
    1.02
     אשר
    1.01
     therefrom
    1.00
     pertanto
    0.99
    Activations Density 0.124%

    No Known Activations