© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5553
    Prev
    Next
    INDEX
    Explanations

    references to personal purpose and life philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "that" and related to "life."

    np_acts-logits-general · gemini-2.0-flash

    life that continued

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.50
     mess
    -0.48
    classnames
    -0.46
     proven
    -0.45
     Entra
    -0.44
    جستارهای
    -0.42
     reinst
    -0.41
     поли
    -0.40
    proven
    -0.40
    alitions
    -0.40
    POSITIVE LOGITS
     life
    0.88
     lifestyle
    0.71
    life
    0.69
     Life
    0.68
    Life
    0.68
     living
    0.65
     happiness
    0.64
     życia
    0.64
     enjoy
    0.63
    人生
    0.63
    Activations Density 0.297%

    No Known Activations