© 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. 16-GEMMASCOPE-RES-16K
    11. 5900
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and data structures related to statistical computations in code

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

    Code or names that appear in all caps

    np_acts-logits-general · gemini-2.0-flash

    numbers and code delimiters

    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
     di
    -0.51
     Cho
    -0.49
     Gar
    -0.48
    \\
    -0.48
     enti
    -0.47
     Bag
    -0.47
     ra
    -0.46
     ry
    -0.46
     survival
    -0.46
    ">//
    -0.45
    POSITIVE LOGITS
    ChildScrollView
    0.96
    GeoNames
    0.84
     EconPapers
    0.80
    +#+#
    0.78
    AnchorStyles
    0.76
    ArgsConstructor
    0.76
     TextInputType
    0.74
     الحره
    0.69
    TargetException
    0.69
     tslint
    0.68
    Activations Density 0.093%

    No Known Activations