© 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. 24-GEMMASCOPE-RES-16K
    11. 4685
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court rulings and damage awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    financial compensation or legal damages

    np_acts-logits-general · gemini-2.0-flash

    compensatory damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.65
    Begriffsklä
    -0.60
     AllAfrica
    -0.52
     surla
    -0.51
     butterknife
    -0.50
    pran
    -0.49
    adaptiveStyles
    -0.48
    спорти
    -0.47
    وفاته
    -0.47
    MenuInflater
    -0.45
    POSITIVE LOGITS
     compensation
    1.25
     damages
    1.21
     compensatory
    1.10
     compensate
    1.03
    Compensation
    1.00
     awards
    0.99
     Damages
    0.99
     award
    0.99
    Dama
    0.97
     recover
    0.96
    Activations Density 1.140%

    No Known Activations