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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46136
    Prev
    Next
    INDEX
    Explanations

    references to legal counsel and corporate governance roles

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

    general counsel and lawyers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    OGND
    -0.59
     CreateTagHelper
    -0.53
    뀔
    -0.51
     '{@
    -0.49
    뀜
    -0.46
    UnusedPrivate
    -0.45
    retweeted
    -0.45
     pedest
    -0.45
     multimodal
    -0.45
    
    -0.44
    POSITIVE LOGITS
     lawyers
    0.75
     lawyer
    0.73
     legal
    0.73
     jurí
    0.67
     Legal
    0.66
     Lawyer
    0.65
     juridiques
    0.64
     Lawyers
    0.63
    lawyer
    0.62
     abogados
    0.62
    Activations Density 0.023%

    No Known Activations