© 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. 22-GEMMASCOPE-RES-16K
    11. 5756
    Prev
    Next
    INDEX
    Explanations

    references to mechanics or features related to the game Minecraft

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

    Follows punctuation, conjunctions, or Japanese text

    np_acts-logits-general · gemini-2.0-flash

    Minecraft redstone and residence

    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
    findpost
    -0.85
     ujednoznacz
    -0.64
    UpInside
    -0.61
    Архівовано
    -0.61
     CreateTagHelper
    -0.61
    Skocz
    -0.59
    MemoryWarning
    -0.56
    complexContent
    -0.56
    UnknownFields
    -0.55
    UserScript
    -0.55
    POSITIVE LOGITS
     Minecraft
    0.84
    minecraft
    0.77
     minecraft
    0.75
     creeper
    0.67
    Minecraft
    0.66
     nether
    0.65
     Nether
    0.64
     block
    0.62
     Ender
    0.60
     ender
    0.60
    Activations Density 0.118%

    No Known Activations