© 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. 9-GEMMASCOPE-RES-16K
    11. 855
    Prev
    Next
    INDEX
    Explanations

    repeated punctuations and their arrangement within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DriverManager
    -0.70
     مشين
    -0.68
    TargetException
    -0.64
    tawesome
    -0.61
    ="@+
    -0.60
    — 
    -0.58
     كومونز
    -0.57
    mybatisplus
    -0.56
    enderror
    -0.56
    prepareStatement
    -0.56
    POSITIVE LOGITS
     resourceCulture
    1.07
    queryInterface
    0.95
    rungsseite
    0.89
    <eos>
    0.81
     MenuView
    0.80
    :✨
    0.78
     disambiguazione
    0.77
    ↵↵
    0.76
    SharedDtor
    0.74
    oredCriteria
    0.71
    Activations Density 0.291%

    No Known Activations