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. 86
    Prev
    Next
    INDEX
    Explanations

    elements and constructs related to JavaScript and web development, particularly involving modal instances and map functionalities

    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
     GenerationType
    -0.69
     CreateTagHelper
    -0.62
     Савезне
    -0.58
    InjectAttribute
    -0.57
     correctes
    -0.56
     فريبيس
    -0.56
     jScrollPane
    -0.55
    enumi
    -0.54
    TintMode
    -0.52
     ◄
    -0.51
    POSITIVE LOGITS
    通
    0.49
     Hook
    0.47
    úgó
    0.46
    tonsoft
    0.46
    ldr
    0.43
    Сам
    0.42
    $}}
    0.42
     giác
    0.42
     vuitton
    0.42
    ible
    0.41
    Activations Density 0.134%

    No Known Activations