© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3795
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal purpose and fulfillment in life

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    hopes and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Basta
    -0.44
    ζει
    -0.42
    Define
    -0.42
    armi
    -0.41
    openSession
    -0.41
    Obituary
    -0.38
    وبه
    -0.38
     dobbiamo
    -0.37
    osob
    -0.37
    loed
    -0.37
    POSITIVE LOGITS
     hoping
    2.19
     expecting
    2.11
     believing
    2.08
     thinking
    2.07
     expectation
    1.94
     assumption
    1.82
     hopes
    1.82
     hoped
    1.78
     Hoping
    1.74
     hope
    1.73
    Activations Density 0.639%

    No Known Activations