© 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. 21-GEMMASCOPE-RES-16K
    11. 14800
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "ten" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی
    -0.56
    subsubsection
    -0.54
    ScopeManager
    -0.53
     eens
    -0.50
     Knapp
    -0.49
    rande
    -0.49
    ValueStyle
    -0.49
     مُعرِّف
    -0.49
    mical
    -0.48
     grat
    -0.47
    POSITIVE LOGITS
     invokingState
    1.04
    AndEndTag
    0.92
     Commandments
    0.89
     commandments
    0.77
    featureID
    0.76
     Downing
    0.74
    ंदीखरीदारी
    0.72
     Tors
    0.71
     kaynağından
    0.70
    0
    0.69
    Activations Density 0.305%

    No Known Activations