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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7444
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and names of places, specifically in the context of geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.52
     relationships
    -0.52
     Amad
    -0.50
    ADORA
    -0.46
     mars
    -0.45
    urti
    -0.45
     Aufbau
    -0.43
    ում
    -0.43
    ↵↵
    -0.43
     Amos
    -0.43
    POSITIVE LOGITS
    
    0.59
    RenderAtEndOf
    0.56
    Parcelize
    0.53
    /**
    0.52
     Exacts
    0.50
    PMailer
    0.45
     bankası
    0.45
    SBATCH
    0.44
     otomatig
    0.43
    icleta
    0.43
    Activations Density 0.171%

    No Known Activations