© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13409
    Prev
    Next
    INDEX
    Explanations

    technical terms related to feature selection in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.96
     houſe
    -0.89
     Houſe
    -0.81
     himſelf
    -0.77
     myſelf
    -0.77
     faſt
    -0.76
    RunAsync
    -0.74
    Бахар
    -0.73
     ſeveral
    -0.73
     themſelves
    -0.70
    POSITIVE LOGITS
     domain
    0.46
     information
    0.45
     pod
    0.44
     Information
    0.43
     users
    0.42
     tasks
    0.42
     cost
    0.42
    AccessorTable
    0.42
     multi
    0.42
    oucí
    0.42
    Activations Density 1.252%

    No Known Activations