© 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. 11-GEMMASCOPE-RES-16K
    11. 4230
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to array manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jerusalén
    -0.53
    bürgermeister
    -0.53
    rceil
    -0.53
     phonetic
    -0.50
     Técnico
    -0.50
     TECN
    -0.49
     EDWIN
    -0.48
    RTLU
    -0.47
    screens
    -0.47
    UGHS
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    InteropServices
    0.66
    MemoryWarning
    0.66
    UrlResolution
    0.65
    djangoproject
    0.63
    tdessen
    0.62
    ImageContext
    0.61
    帖最后由
    0.60
    ibatis
    0.59
     resourceCulture
    0.59
    Activations Density 0.048%

    No Known Activations