© 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. 16-GEMMASCOPE-RES-16K
    11. 1245
    Prev
    Next
    INDEX
    Explanations

    structures or data representations related to coding or programming

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

    Minecraft

    np_acts-logits-general · gemini-2.0-flash

    minecraft, terraria, video games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laurel
    -0.48
    Архівовано
    -0.48
    aguer
    -0.47
    PointSize
    -0.47
    xane
    -0.47
     Balboa
    -0.45
    whel
    -0.45
    acabana
    -0.44
     coached
    -0.44
    nase
    -0.43
    POSITIVE LOGITS
    minecraft
    1.29
     Terraria
    1.02
    bukkit
    0.99
     Minecraft
    0.98
    minecraftforge
    0.89
    Minecraft
    0.87
     minecraft
    0.75
     Roblox
    0.70
    bewerken
    0.69
    Datuak
    0.68
    Activations Density 0.048%

    No Known Activations