© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 4797
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and function-related elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.88
     ModelExpression
    -0.81
    twimg
    -0.80
     nahilalakip
    -0.80
    PreferredItem
    -0.79
     EClass
    -0.78
    MessageOf
    -0.77
    stateProvider
    -0.75
    >`;
    -0.75
    canestro
    -0.75
    POSITIVE LOGITS
     оригіналу
    0.42
     thinking
    0.42
    őd
    0.42
     Zwiebel
    0.42
     cause
    0.42
    程
    0.42
    UpdateUser
    0.41
     mungkin
    0.41
    μί
    0.40
     forever
    0.39
    Activations Density 0.024%

    No Known Activations