© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1867
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data analysis and gaming mechanics

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

    Code-related syntax and keywords

    np_acts-logits-general · gemini-2.0-flash

    game configuration and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.44
     professora
    -0.40
     Schützen
    -0.37
     peserta
    -0.37
     exercícios
    -0.37
     Hochschule
    -0.36
     deltag
    -0.36
    праж
    -0.35
     Bür
    -0.35
     coffees
    -0.35
    POSITIVE LOGITS
    minecraft
    1.02
     Terraria
    0.79
     Minecraft
    0.71
     minecraft
    0.67
    fml
    0.64
     mods
    0.58
    minecraftforge
    0.58
    Minecraft
    0.56
     modded
    0.55
     biome
    0.54
    Activations Density 0.063%

    No Known Activations