© 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. 8-GEMMASCOPE-RES-16K
    11. 10611
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data types in code, particularly involving templates and structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.88
     Roskov
    -0.83
    tonode
    -0.83
    SBATCH
    -0.81
     onOptions
    -0.81
    expandindo
    -0.78
    AsStream
    -0.77
    CppMethod
    -0.75
     onPostExecute
    -0.74
     purpoſe
    -0.74
    POSITIVE LOGITS
     fu
    0.53
    vol
    0.53
    unna
    0.52
     "..\..\..\
    0.51
    æd
    0.50
     Ek
    0.48
    vil
    0.48
    ols
    0.48
    int
    0.47
     Tan
    0.47
    Activations Density 0.789%

    No Known Activations