© 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. 20-GEMMASCOPE-RES-16K
    11. 14948
    Prev
    Next
    INDEX
    Explanations

    words related to assistance and support

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

    following "help" or "helps"

    np_acts-logits-general · gemini-2.0-flash

    acts of helping understand

    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
     للاسماء
    -0.60
    be
    -0.58
    use
    -0.55
    🎳
    -0.54
     soient
    -0.53
    timeScale
    -0.52
    Personensuche
    -0.52
     للمعارف
    -0.51
     capaz
    -0.51
    saraba
    -0.51
    POSITIVE LOGITS
    fully
    0.90
     solve
    0.82
     facilitate
    0.75
     improve
    0.74
     strengthen
    0.72
     alleviate
    0.71
    desk
    0.71
     propOrder
    0.71
     ensure
    0.69
     protect
    0.67
    Activations Density 0.056%

    No Known Activations