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. 1-GEMMASCOPE-RES-16K
    6. 9654
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to XAML markup and presentation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unters
    -0.52
     termica
    -0.51
    municipi
    -0.51
     Licensed
    -0.48
     ANO
    -0.48
    illermo
    -0.47
    олові
    -0.46
     licensed
    -0.45
    newData
    -0.45
     χώ
    -0.44
    POSITIVE LOGITS
    Autoritní
    0.83
     initWithFrame
    0.68
    xaml
    0.64
    NameInMap
    0.63
     linkovi
    0.62
    Дереккөздер
    0.61
     Normdatei
    0.60
    DebuggerStep
    0.59
    multer
    0.58
    ::$
    0.57
    Activations Density 1.912%

    No Known Activations