© 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. 14381
    Prev
    Next
    INDEX
    Explanations

    phrases relating to personal purpose and life's trajectory

    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
     chi̍t
    -0.62
    SpringBootTest
    -0.57
    InputBorder
    -0.50
    orghe
    -0.45
    igera
    -0.42
    gonic
    -0.42
    󠁢
    -0.42
    ỏng
    -0.42
    पया
    -0.42
    yg
    -0.42
    POSITIVE LOGITS
     life
    3.10
    life
    2.52
     Life
    2.28
     LIFE
    2.26
    Life
    2.22
     lives
    2.21
    LIFE
    2.13
     vida
    2.05
     жизни
    1.95
     Leben
    1.80
    Activations Density 0.295%

    No Known Activations