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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6961
    Prev
    Next
    INDEX
    Explanations

    references to Chinese and other Asian nationalities or ethnicities

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

    nationalities or origins

    np_acts-logits-general · gemini-2.0-flash

    nationalities and their associated terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     گردد
    -0.43
    噜
    -0.41
     tunik
    -0.41
     Gelände
    -0.41
    ddots
    -0.41
     کیلو
    -0.41
    höhe
    -0.40
     škola
    -0.40
     škole
    -0.40
     joy
    -0.39
    POSITIVE LOGITS
    Chinese
    1.21
    Japanese
    1.20
     Chinese
    1.20
    Russian
    1.20
     Russian
    1.20
     Japanese
    1.18
    Mexican
    1.15
    Italian
    1.13
    Indian
    1.13
     German
    1.12
    Activations Density 0.290%

    No Known Activations