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. 16-GEMMASCOPE-RES-16K
    6. 12543
    Prev
    Next
    INDEX
    Explanations

    specific programming terminology related to software development and data processing structures

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

    Code, file paths, and directory-related words

    np_acts-logits-general · gemini-2.0-flash

    Audio session

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.88
    อาด
    -0.75
     endregion
    -0.75
    IUrlHelper
    -0.72
     '{@
    -0.70
     propOrder
    -0.68
    contentLoaded
    -0.65
     AssemblyCompany
    -0.65
    ">//
    -0.64
     ویکی‌پدیای
    -0.63
    POSITIVE LOGITS
    tonsoft
    0.59
    ьаж
    0.51
    LLocation
    0.50
    PyTuple
    0.50
    Parcelable
    0.50
    таратура
    0.47
    MutableLiveData
    0.47
    medriver
    0.45
     kasarigan
    0.45
    #+#
    0.44
    Activations Density 1.136%

    No Known Activations