© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4563
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings and claims

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

    Legal and tax contexts

    np_acts-logits-general · gemini-2.0-flash

    taxpayer procedure or legal action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.62
    OGND
    -0.62
    DeleteBehavior
    -0.61
     المعيارى
    -0.59
    хьтан
    -0.59
     uncons
    -0.56
     exoner
    -0.56
     exempted
    -0.56
     henvisninger
    -0.55
     hereby
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.40
     betweenstory
    0.37
     STUFF
    0.29
     Auseinander
    0.27
    方面
    0.27
    SequentialGroup
    0.26
     fidèle
    0.26
     souvent
    0.26
    Grüsse
    0.26
     Ahnung
    0.26
    Activations Density 1.107%

    No Known Activations