Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tắt
    -0.61
    OGND
    -0.59
     MenuView
    -0.56
     disambiguazione
    -0.52
    MessageTagHelper
    -0.50
    ]){
    
    -0.48
     Autorisations
    -0.48
     decorativas
    -0.48
    AndroidJUnit
    -0.48
     OFDb
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.67
     تضيفلها
    0.62
    awtextra
    0.58
    ogy
    0.57
     einz
    0.57
    __*/
    0.55
    JAXB
    0.53
    oxone
    0.52
    тья
    0.52
    CloseOperation
    0.51
    Activations Density 0.778%

    No Known Activations