© 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. 6859
    Prev
    Next
    INDEX
    Explanations

    elements related to movement and action in a gaming or role-playing context

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

    RPG or tabletop game mechanics

    np_acts-logits-general · gemini-2.0-flash

    RPGs and spells

    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
     jScrollPane
    -0.59
    AsUp
    -0.59
     Chrift
    -0.54
    AutoScaleMode
    -0.54
    requireNonNull
    -0.52
     adiós
    -0.52
     traffic
    -0.51
     Chriſt
    -0.51
     Reſ
    -0.51
     AssemblyCulture
    -0.50
    POSITIVE LOGITS
     campaign
    0.71
     PCs
    0.68
     DM
    0.63
    campaign
    0.63
     snippetHide
    0.62
     roll
    0.61
     CAMPAIGN
    0.60
     campagna
    0.58
     campanha
    0.58
     sessão
    0.57
    Activations Density 0.141%

    No Known Activations