© 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. 97320
    Prev
    Next
    INDEX
    Explanations

    references to the character 'Celia' and her interactions, particularly in a legal or contractual context

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

    Ce followed by Celia or Cl

    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
     chrétienne
    -0.53
     baskılı
    -0.49
     the
    -0.49
     pédagogique
    -0.48
     mauva
    -0.47
     étrang
    -0.46
     étrangère
    -0.46
     puissante
    -0.46
     renfor
    -0.46
     overwhelmingly
    -0.46
    POSITIVE LOGITS
     Ce
    2.05
    Ce
    1.96
     ce
    1.62
     CE
    1.31
     Celia
    1.24
    CE
    1.08
    ce
    1.03
     Cé
    1.00
    Cé
    0.97
     Cet
    0.95
    Activations Density 0.013%

    No Known Activations