© 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. 8745
    Prev
    Next
    INDEX
    Explanations

    blocks of code, specifically focusing on control flow structures like conditional statements and closures

    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
    copyWith
    -0.55
     Tyr
    -0.47
    余
    -0.44
     Pil
    -0.44
    paris
    -0.43
    libft
    -0.43
    ponses
    -0.43
     Ush
    -0.42
     Paris
    -0.42
    cises
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.80
     endforeach
    0.79
     ***!
    0.79
    GEBURTSDATUM
    0.79
     étroite
    0.69
    principalTable
    0.68
    addContainerGap
    0.67
    AndEndTag
    0.67
    MessageTagHelper
    0.66
    UnsafeEnabled
    0.66
    Activations Density 0.067%

    No Known Activations