© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7826
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or identifiers

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

    Hexadecimal byte representations

    np_acts-logits-general · gemini-2.0-flash

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.41
    expandindo
    -0.41
    füh
    -0.40
    copg
    -0.38
    GNUC
    -0.37
    ɵ
    -0.36
    ьаж
    -0.35
    stateMutability
    -0.35
     pie
    -0.34
    unmodifiable
    -0.34
    POSITIVE LOGITS
     informée
    0.69
     وتسجيلات
    0.66
     يتيمه
    0.66
     للمعارف
    0.65
     autorytatywna
    0.61
    MessageTagHelper
    0.59
    -------
    0.56
    はじめに
    0.56
    
    0.55
    tagHelperRunner
    0.54
    Activations Density 0.683%

    No Known Activations