© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 1237
    Prev
    Next
    INDEX
    Explanations

    references to core libraries or modules in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awt
    -0.76
    TypedDataSet
    -0.58
     {}),
    -0.51
    bukkit
    -0.51
    ungk
    -0.50
    appcompat
    -0.48
     proving
    -0.47
    signup
    -0.46
     area
    -0.45
    <bos>
    -0.45
    POSITIVE LOGITS
    core
    1.04
    Geplaatst
    1.02
    ReusableCell
    0.95
    #+#
    0.92
    ValueStyle
    0.86
    ContentAsync
    0.83
     ویکی‌پدیا
    0.81
    Core
    0.81
    MessageTagHelper
    0.80
    帖最后由
    0.80
    Activations Density 0.014%

    No Known Activations