© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    economic development and growth within specific industries

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

    a change or shift

    np_acts-logits-general · gemini-2.0-flash

    change and transition

    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
     المعيارى
    -0.64
     tomorrow
    -0.60
     ويكيميديا
    -0.58
    Bronnen
    -0.58
     kategor
    -0.54
    ihnachts
    -0.54
    falgar
    -0.54
    quelize
    -0.53
     domani
    -0.53
    erevan
    -0.53
    POSITIVE LOGITS
     ushered
    0.84
     began
    0.82
    Beginning
    0.80
     culminated
    0.79
     coincided
    0.79
     gradually
    0.79
     culminating
    0.78
     beginning
    0.77
     largely
    0.76
     spearheaded
    0.75
    Activations Density 0.744%

    No Known Activations