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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7972
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and formulations related to statistics and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.65
    rungsseite
    -0.58
    IntoConstraints
    -0.57
    gameserver
    -0.53
    
    -0.52
    ьаж
    -0.52
     ujednoznacz
    -0.51
    parsedMessage
    -0.50
    ActionEvent
    -0.50
     Photocase
    -0.50
    POSITIVE LOGITS
    sqrt
    1.89
     root
    1.88
     sqrt
    1.81
    root
    1.75
     Root
    1.71
    Root
    1.65
     roots
    1.63
    Sqrt
    1.55
     √
    1.54
    √
    1.54
    Activations Density 1.101%

    No Known Activations