© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8611
    Prev
    Next
    INDEX
    Explanations

    references to relationships and interactions among individuals or groups

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

    followed by "being" or similar words

    np_acts-logits-general · gemini-2.0-flash

    state of being

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
    getreten
    -0.56
     दें
    -0.53
     disediakan
    -0.51
     sahiptir
    -0.49
    lanır
    -0.49
    りは
    -0.49
    Termine
    -0.46
     sağlar
    -0.46
    жмите
    -0.45
    founded
    -0.44
    POSITIVE LOGITS
     being
    3.01
    being
    2.43
     BEING
    2.19
    Being
    2.11
     becoming
    2.06
     having
    2.03
     Being
    2.00
     étant
    1.79
     getting
    1.75
     fiind
    1.73
    Activations Density 0.599%

    No Known Activations