© 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. 24-GEMMASCOPE-RES-16K
    11. 8787
    Prev
    Next
    INDEX
    Explanations

    concepts related to work-life balance and systemic interrelationships

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

    relationships or equivalence

    np_acts-logits-general · gemini-2.0-flash

    mutually related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Association
    -0.57
     Association
    -0.53
     Asso
    -0.52
     Ceux
    -0.51
    깥
    -0.51
     Kombination
    -0.50
     próprio
    -0.49
     association
    -0.48
    association
    -0.47
     ASSOCIATION
    -0.47
    POSITIVE LOGITS
     mutually
    0.90
     inter
    0.85
     interdependent
    0.81
     interrelated
    0.73
     co
    0.73
    inter
    0.72
     서
    0.71
     complementary
    0.71
     intertwined
    0.70
     sharing
    0.69
    Activations Density 0.668%

    No Known Activations