© 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. 14661
    Prev
    Next
    INDEX
    Explanations

    words related to relaxation and personal hobbies

    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
    makaian
    -0.51
     plasti
    -0.50
    ilí
    -0.50
     entusias
    -0.49
    rigin
    -0.47
     &___
    -0.47
    hyrchwyd
    -0.46
     AssemblyProduct
    -0.46
    胱
    -0.45
    joined
    -0.45
    POSITIVE LOGITS
     relaxation
    1.65
     relax
    1.57
    relax
    1.51
     relaxing
    1.46
     Relaxation
    1.43
     Relax
    1.40
    Relax
    1.38
     unwind
    1.30
     relaxes
    1.29
     rilass
    1.16
    Activations Density 0.157%

    No Known Activations