© 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. 7895
    Prev
    Next
    INDEX
    Explanations

    frequency adverbs and modifiers that express certainty or emphasis

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

    Follows adverbs of emphasis

    np_acts-logits-general · gemini-2.0-flash

    qualifying adverbs

    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
     finalement
    -0.88
     schließlich
    -0.80
     ultimately
    -0.77
     específicamente
    -0.75
     AssemblyTitle
    -0.75
    finally
    -0.74
     ciertamente
    -0.71
     eventually
    -0.71
     particularmente
    -0.71
    SBATCH
    -0.71
    POSITIVE LOGITS
     speaking
    0.90
    ً
    0.72
    mente
    0.71
     оригіналу
    0.71
    แล้ว
    0.70
    speaking
    0.70
    šnje
    0.68
     говоря
    0.64
    情况下
    0.64
     تضيفلها
    0.63
    Activations Density 0.469%

    No Known Activations