© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4283
    Prev
    Next
    INDEX
    Explanations

    references to French culture, people, and geographic locations

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

    the French language or culture

    np_acts-logits-general · gemini-2.0-flash

    french descriptor

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    •Gemma 2 9B Subliminal Learning

    No Comments

    Negative Logits
     disambiguazione
    -0.71
    uxxxx
    -0.66
    énario
    -0.65
    Personendaten
    -0.65
     utafitiHapana
    -0.60
    ंदीखरीदारी
    -0.60
    setVerticalGroup
    -0.59
     betweenstory
    -0.58
    expandindo
    -0.53
    AutoScale
    -0.52
    POSITIVE LOGITS
     French
    1.43
    French
    1.28
     France
    1.28
     french
    1.17
     franceses
    1.13
    France
    1.10
     francês
    1.09
     Frankreich
    1.09
     FRENCH
    1.09
     francés
    1.05
    Activations Density 0.240%

    No Known Activations