© 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. 5-GEMMASCOPE-RES-16K
    11. 14065
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies or research formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Réalisation
    -0.78
    TagMode
    -0.75
    SPATH
    -0.71
     Italijanski
    -0.68
    makaian
    -0.67
    aarrggbb
    -0.66
     neceff
    -0.64
     Italijani
    -0.64
    testcase
    -0.63
    Sqft
    -0.62
    POSITIVE LOGITS
    ValueStyle
    0.56
    </thead>
    0.49
    XmlEnum
    0.48
    ReusableCell
    0.46
    èdia
    0.45
     AssemblyCulture
    0.45
    下载附件
    0.44
    Hall
    0.44
     QName
    0.43
    EndInit
    0.43
    Activations Density 1.648%

    No Known Activations