Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 315
    Prev
    Next
    INDEX
    Explanations

    materials and specific components related to construction and manufacturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to materials, particularly metals and construction materials.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.75
     تانيه
    -0.72
    tagHelperRunner
    -0.65
    hydrox
    -0.63
     ◄
    -0.63
    PositiveButton
    -0.61
    MessageTagHelper
    -0.61
    gars
    -0.59
     Infórmanos
    -0.59
    :].
    -0.59
    POSITIVE LOGITS
    TagHelpers
    0.60
    クリート
    0.49
     kiin
    0.46
    jsonPath
    0.45
    製の
    0.45
     lined
    0.45
    hasMoreElements
    0.43
    stdint
    0.43
    -
    0.43
     venner
    0.43
    Activations Density 0.540%

    No Known Activations