© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    words related to vigorous or dynamic actions and characteristics, particularly those associated with energy and activity

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

    that start with "vig," "rig," or "sig"

    np_acts-logits-general · gemini-2.0-flash

    vig, rig, sig, zig prefixes

    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
    ThroughAttribute
    -0.85
     оригіналу
    -0.84
     SPDX
    -0.80
     resourceCulture
    -0.77
    LookAnd
    -0.70
    談社
    -0.69
     ostavi
    -0.69
     متعلقه
    -0.67
    Rhestr
    -0.63
     שוליים
    -0.62
    POSITIVE LOGITS
     Rig
    0.71
     rig
    0.66
    Rig
    0.66
    Hig
    0.65
    Wig
    0.65
     VIG
    0.64
     RIG
    0.62
    Vig
    0.62
     Vig
    0.61
    vig
    0.60
    Activations Density 0.198%

    No Known Activations