© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3599
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures, particularly focusing on nested data types and fields in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tzmann
    -0.52
    MenuBar
    -0.48
    Geografie
    -0.48
    Com
    -0.47
    ipan
    -0.45
     gre
    -0.44
     getopt
    -0.43
    pani
    -0.43
    enetic
    -0.42
     sk
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.98
    MLLoader
    0.79
    Datuak
    0.77
    Diwedd
    0.72
    ">//
    0.68
     purpoſe
    0.65
     itſelf
    0.64
    GIVEREF
    0.64
     ſever
    0.64
     quæ
    0.63
    Activations Density 0.944%

    No Known Activations