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. 1513
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical operations and relationships, particularly those involving division and grouping

    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
     Обе
    -0.41
    Bound
    -0.39
     presenti
    -0.39
     تل
    -0.39
    pius
    -0.37
     surround
    -0.37
     sit
    -0.37
     ri
    -0.36
    wer
    -0.36
     marche
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.96
    parsedMessage
    0.87
     pinulongan
    0.84
    __*/
    0.84
    rungsseite
    0.81
    Geplaatst
    0.77
    IUrlHelper
    0.74
     المعيارى
    0.73
    참고
    0.73
    原始内容存档于
    0.71
    Activations Density 0.759%

    No Known Activations