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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13674
    Prev
    Next
    INDEX
    Explanations

    mentions of technical terms and concepts related to system architecture and performance

    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
    createClass
    -0.66
    Продам
    -0.66
     embri
    -0.63
     disambiguazione
    -0.62
     createState
    -0.62
     يتيمه
    -0.61
    :✨
    -0.61
    windowFixed
    -0.59
    ướt
    -0.59
    ///</
    -0.59
    POSITIVE LOGITS
     فريبيس
    0.50
    表示
    0.49
    겠
    0.49
    DeleteBehavior
    0.47
    INARY
    0.47
    Diwedd
    0.46
    Vaya
    0.46
    CardBody
    0.45
    Yii
    0.45
     Generale
    0.44
    Activations Density 2.431%

    No Known Activations