© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 461
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.15
     Jefus
    -1.05
     purpoſe
    -0.99
     Theſe
    -0.98
     pleaſure
    -0.94
     Chriftian
    -0.92
     greateſt
    -0.92
     Anſ
    -0.90
     myſelf
    -0.88
     themſelves
    -0.88
    POSITIVE LOGITS
     law
    2.86
     Law
    2.63
     LAW
    2.48
    Law
    2.43
    law
    2.39
     laws
    2.22
    LAW
    2.15
     Laws
    1.93
    laws
    1.69
     LAWS
    1.66
    Activations Density 0.059%

    No Known Activations