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. 14-GEMMASCOPE-RES-16K
    6. 3075
    Prev
    Next
    INDEX
    Explanations

    components and coding structures related to job card applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.86
    rawDesc
    -0.74
    interopRequire
    -0.70
    CloseOperation
    -0.67
    sizeCache
    -0.67
     Paglinawan
    -0.65
     Kamil
    -0.64
    printStackTrace
    -0.62
    CppMethod
    -0.62
     ChromeDriver
    -0.62
    POSITIVE LOGITS
    IZI
    0.49
     الحره
    0.49
    τας
    0.48
     SwiftUI
    0.47
    .*")]
    0.47
    Elems
    0.47
     varandra
    0.47
    claimer
    0.46
     StatelessWidget
    0.46
    ῖ
    0.45
    Activations Density 0.050%

    No Known Activations