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. 15-GEMMASCOPE-RES-16K
    6. 8785
    Prev
    Next
    INDEX
    Explanations

    references to data structure handling in programming, particularly involving Bundles in Android

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gough
    -0.79
     tatouage
    -0.75
     fuoco
    -0.74
     Lips
    -0.73
    BeginContext
    -0.69
     Ains
    -0.69
    itext
    -0.67
    getWriter
    -0.67
     [](
    -0.66
    او
    -0.65
    POSITIVE LOGITS
    Bundle
    1.46
     Bundle
    1.34
     bundle
    1.32
    Bundles
    1.22
     bundles
    1.21
    bundle
    1.21
    bundles
    1.18
    UNDLE
    1.11
     Bund
    1.09
     يتيمه
    0.97
    Activations Density 0.088%

    No Known Activations