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. 14315
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to court decisions and rulings

    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
    Personensuche
    -0.81
     >=",
    -0.75
    Personendaten
    -0.70
    saraba
    -0.69
     ModelExpression
    -0.66
    nologue
    -0.60
    脚注の使い方
    -0.60
    ">//
    -0.57
    IsMutable
    -0.56
     Waray
    -0.54
    POSITIVE LOGITS
     responsibility
    1.06
     onus
    0.97
    responsibility
    0.95
    Responsibility
    0.89
     responsabilidad
    0.89
     Responsibility
    0.88
     compito
    0.82
     Aufgabe
    0.81
     decision
    0.80
     decide
    0.79
    Activations Density 0.306%

    No Known Activations