© 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. 18-GEMMASCOPE-RES-16K
    11. 11739
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terminology related to commissions and proceedings

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

    followed by "being" or "would"

    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 @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighed
    -0.54
    getreten
    -0.51
    りは
    -0.51
     disediakan
    -0.50
    founded
    -0.48
    oko
    -0.48
    ustomed
    -0.47
     दें
    -0.45
    lanır
    -0.45
    aboo
    -0.45
    POSITIVE LOGITS
     being
    2.84
    being
    2.30
     BEING
    2.12
    Being
    2.02
     Being
    1.91
     becoming
    1.81
     having
    1.78
     étant
    1.67
     fiind
    1.65
     sendo
    1.65
    Activations Density 0.589%

    No Known Activations