© 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. 4279
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'sund' or 'health'

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

    starting with "Und" or "Sund"

    np_acts-logits-general · gemini-2.0-flash

    Undaria, undoubtedly, Sundberg

    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
     MenuView
    -0.56
     căr
    -0.54
     urmă
    -0.54
     äm
    -0.53
     besos
    -0.52
     diret
    -0.49
    +#+#
    -0.49
     obstante
    -0.47
     خارجية
    -0.47
     références
    -0.47
    POSITIVE LOGITS
     Mund
    0.76
    UND
    0.76
     Gund
    0.75
    Mund
    0.72
    Kund
    0.70
    sund
    0.70
     UND
    0.69
     Kund
    0.69
    Sund
    0.65
     Grund
    0.64
    Activations Density 0.113%

    No Known Activations