© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44210
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts and definitions

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

    any person or entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.54
     amplifiers
    -0.54
     nahilalakip
    -0.53
     quilts
    -0.52
     scooters
    -0.50
     devices
    -0.50
     själva
    -0.50
     eds
    -0.50
     cottages
    -0.49
    novel
    -0.49
    POSITIVE LOGITS
     person
    1.33
     someone
    0.94
    someone
    0.91
     personne
    0.91
     member
    0.89
    person
    0.88
     somebody
    0.88
     osoba
    0.86
     pessoa
    0.83
     perſon
    0.78
    Activations Density 0.142%

    No Known Activations