© 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. 6-GEMMASCOPE-RES-16K
    11. 6732
    Prev
    Next
    INDEX
    Explanations

    structured data formats and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.68
    UnsafeEnabled
    -0.66
     kasarigan
    -0.65
    twimg
    -0.64
    Zacks
    -0.62
    Примітки
    -0.59
    mybatisplus
    -0.58
    تقاوى
    -0.57
     المعيارى
    -0.57
    IonicModule
    -0.56
    POSITIVE LOGITS
    __(/*!
    0.66
     ↑
    0.64
    omiast
    0.61
    itzende
    0.61
    //
    0.59
    ⦁
    0.59
    ︎
    0.58
     tục
    0.58
    alians
    0.57
    $",
    0.57
    Activations Density 0.273%

    No Known Activations