© 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. 21-GEMMASCOPE-RES-16K
    11. 14745
    Prev
    Next
    INDEX
    Explanations

    statistical terms and calculations related to averages and variances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šli
    -0.45
     يتيمه
    -0.45
    Few
    -0.43
    ™
    -0.42
     Especially
    -0.42
    Especially
    -0.42
    fsp
    -0.41
     Particularly
    -0.40
    辞典
    -0.40
    withstanding
    -0.38
    POSITIVE LOGITS
     minus
    1.43
    minus
    1.15
     multiplied
    1.14
     subtracted
    1.06
     divided
    1.02
     plus
    1.01
     times
    0.99
     subtract
    0.97
     subtracting
    0.96
     Minus
    0.94
    Activations Density 1.418%

    No Known Activations