© 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. 15822
    Prev
    Next
    INDEX
    Explanations

    references to specific game mechanics or items

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

    Character classes or races

    np_acts-logits-general · gemini-2.0-flash

    game character classes

    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
    DockStyle
    -1.04
    tvguidetime
    -0.96
    InputBorder
    -0.90
    SBATCH
    -0.89
     getItemId
    -0.81
    WaitGroup
    -0.77
    AndEndTag
    -0.77
     habet
    -0.72
    Tembelea
    -0.72
     quæ
    -0.71
    POSITIVE LOGITS
     female
    0.46
    చు
    0.46
    ghar
    0.42
     Shaman
    0.42
     shaman
    0.42
     male
    0.42
     classe
    0.41
     Mene
    0.41
     Sor
    0.41
     sor
    0.40
    Activations Density 0.126%

    No Known Activations