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. 2-GEMMASCOPE-RES-16K
    6. 15047
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related phrases in programming and software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shift
    -0.54
    бур
    -0.52
    __':
    -0.49
    shift
    -0.48
     ↑
    -0.47
    <<"
    -0.45
     commitment
    -0.44
     <<"
    -0.43
    genommen
    -0.43
    ворот
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.91
    WebElementEntity
    0.86
    IUrlHelper
    0.78
     betweenstory
    0.75
    ValueGeneration
    0.69
    )_/¯
    0.69
     TextAppearance
    0.68
    تقاوى
    0.67
     itſelf
    0.67
    PMailer
    0.67
    Activations Density 3.670%

    No Known Activations