© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7739
    Prev
    Next
    INDEX
    Explanations

    numeric data and structured information, potentially indicating a focus on statistical or quantitative details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.98
    ChildScrollView
    -0.94
     ISNI
    -0.90
    RectangleBorder
    -0.90
    सन्दर्भ
    -0.83
     StatelessWidget
    -0.81
    UnknownFields
    -0.78
     StatefulWidget
    -0.78
    }{*}{}
    -0.76
    ElementException
    -0.76
    POSITIVE LOGITS
     Réponses
    0.48
    قیمت
    0.43
    ing
    0.42
     dec
    0.41
    ooze
    0.41
    تعداد
    0.41
    픈
    0.40
    крыть
    0.40
    AndroidJUnit
    0.39
     Nor
    0.39
    Activations Density 0.842%

    No Known Activations