© 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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15774
    Prev
    Next
    INDEX
    Explanations

    references to video game systems and software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Вікі
    -0.47
    AnchorStyles
    -0.44
    IVEREF
    -0.41
    ApiOperation
    -0.41
     FontWeight
    -0.41
    webElementXpaths
    -0.40
    RenderAtEndOf
    -0.39
    imread
    -0.39
     ESO
    -0.39
     Benedict
    -0.36
    POSITIVE LOGITS
     cartridge
    0.77
     arcade
    0.74
     cartridges
    0.70
     SNES
    0.68
     Atari
    0.68
     Commodore
    0.67
     NES
    0.66
     Sinclair
    0.63
    arcade
    0.61
     retro
    0.60
    Activations Density 0.252%

    No Known Activations