© 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. 22-GEMMASCOPE-RES-16K
    11. 6677
    Prev
    Next
    INDEX
    Explanations

    words related to game mechanics and player actions

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

    Nintendo games and related terms

    np_acts-logits-general · gemini-2.0-flash

    Nintendo games and consoles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.66
    الحياه
    -0.61
    VIAF
    -0.61
     GenerationType
    -0.57
    Архівовано
    -0.56
     typelib
    -0.55
     Minang
    -0.54
     Piotr
    -0.53
     Minangkabau
    -0.53
     PTS
    -0.52
    POSITIVE LOGITS
     Nintendo
    1.12
     Mario
    1.05
     Zelda
    1.03
     Switch
    0.94
    Nintendo
    0.92
    Mario
    0.90
     nintendo
    0.85
     Bowser
    0.85
    Zelda
    0.85
     mario
    0.84
    Activations Density 0.109%

    No Known Activations