© 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. 9-GEMMASCOPE-RES-131K
    11. 45536
    Prev
    Next
    INDEX
    Explanations

    references to civil matters and issues in society

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

    civil war, servants, rights, status, society

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ausrüstung
    -0.46
     Backman
    -0.44
    myapplication
    -0.43
     Marken
    -0.42
     Verpackung
    -0.42
     Atkinson
    -0.41
     vôtre
    -0.41
     whereabouts
    -0.40
     Jepang
    -0.40
     Mittelalter
    -0.40
    POSITIVE LOGITS
     civil
    1.38
    civil
    1.23
    Civil
    1.06
     Civil
    0.95
     CIVIL
    0.94
     civile
    0.81
     civility
    0.81
     civils
    0.79
     civi
    0.75
     civili
    0.73
    Activations Density 0.004%

    No Known Activations