© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15400
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "several" and its related numerical values

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

    Quantities or numbers

    np_acts-logits-general · gemini-2.0-flash

    several followed by quantities

    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
    ////////////////
    -0.58
     Miki
    -0.58
    gridx
    -0.57
    –
    -0.55
    MessageTagHelper
    -0.55
     BoxDecoration
    -0.52
    WindowEvent
    -0.51
     TextStyle
    -0.51
     salva
    -0.51
    oucí
    -0.51
    POSITIVE LOGITS
     hundred
    1.31
     thousand
    1.19
     dozen
    1.15
    hundred
    1.01
     dizaines
    1.00
    dozen
    0.94
    thousand
    0.90
     centaines
    0.89
    Hundred
    0.89
     '{@
    0.87
    Activations Density 0.271%

    No Known Activations