© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12908
    Prev
    Next
    INDEX
    Explanations

    numerical values and fractions within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.71
    tagHelperRunner
    -0.68
     <<<<<<<<<<<<<<
    -0.67
    +#+#
    -0.65
    InjectAttribute
    -0.64
     Meksiku
    -0.63
    لينكات
    -0.62
    featureID
    -0.61
    CloseOperation
    -0.61
    ➟
    -0.60
    POSITIVE LOGITS
     culturelles
    0.62
     économies
    0.57
     pensées
    0.56
     financières
    0.56
     démocr
    0.56
     leçons
    0.55
     humaines
    0.55
     publiques
    0.54
    IsPostBack
    0.54
     besky
    0.53
    Activations Density 0.259%

    No Known Activations