© 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. 24-GEMMASCOPE-RES-16K
    11. 3800
    Prev
    Next
    INDEX
    Explanations

    actions and functions related to software and digital processes

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

    Comes before "for" or "with" or "in"

    np_acts-logits-general · gemini-2.0-flash

    easily and anytime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yoksa
    -0.61
    才能
    -0.60
    才行
    -0.56
     demais
    -0.54
    才会
    -0.54
    liesslich
    -0.53
    pires
    -0.53
    TextAppearance
    -0.51
    necessarily
    -0.51
    QRST
    -0.51
    POSITIVE LOGITS
     easily
    2.05
     fácilmente
    1.77
    easily
    1.75
     anytime
    1.73
     facilmente
    1.68
     facilement
    1.56
     Easily
    1.49
     any
    1.45
     anywhere
    1.43
    Easily
    1.43
    Activations Density 0.711%

    No Known Activations