Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     showcased
    -0.76
     transitioning
    -0.76
     showcasing
    -0.74
     otomatig
    -0.71
     impactful
    -0.69
     showcases
    -0.68
     impacting
    -0.67
     transitioned
    -0.65
    脚注の使い方
    -0.65
     onboarding
    -0.65
    POSITIVE LOGITS
     skall
    0.74
     forthwith
    0.73
     muß
    0.70
     doubtless
    0.67
     manifestly
    0.65
     thence
    0.59
     läßt
    0.58
     mußte
    0.56
     ibid
    0.56
     gewiß
    0.56
    Activations Density 0.853%

    No Known Activations