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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64662
    Prev
    Next
    INDEX
    Explanations

    the word "lieu" indicating a substitution or alternative context

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

    instead of

    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
    -```
    -0.40
     rodríguez
    -0.38
    pektive
    -0.38
    andaag
    -0.36
     folle
    -0.36
     αὐ
    -0.35
     Sehingga
    -0.35
     Schuster
    -0.35
     Weltkrieg
    -0.35
     brutal
    -0.34
    POSITIVE LOGITS
     lieu
    0.70
    extAlignment
    0.63
     Lieu
    0.61
     ब्रेकडाउन
    0.60
    出版年
    0.59
    ंदीखरीदारी
    0.57
     <>",
    0.56
    complexContent
    0.52
    IntoConstraints
    0.51
    XmlAccessType
    0.50
    Activations Density 0.003%

    No Known Activations