© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56213
    Prev
    Next
    INDEX
    Explanations

    references to programming and technical concepts related to coding, particularly within the context of the Minecraft game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.96
    IndentedString
    -0.73
    MessageTagHelper
    -0.72
    mpotent
    -0.71
     cesse
    -0.69
    NullException
    -0.68
    NewUrlParser
    -0.68
     AssemblyCompany
    -0.68
    AsUp
    -0.67
    ainville
    -0.67
    POSITIVE LOGITS
    minecraft
    0.79
    </thead>
    0.74
    textTheme
    0.62
    nbt
    0.58
     Henn
    0.58
    Похо
    0.57
    Leng
    0.55
    생
    0.54
    jectures
    0.52
     AppCompat
    0.52
    Activations Density 0.002%

    No Known Activations