© 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. 10-GEMMASCOPE-RES-16K
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    the beginning of a text or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.76
    ItemBackground
    -0.63
    SpringRunner
    -0.55
    ksikon
    -0.55
    ItemLayout
    -0.54
    audiovisuel
    -0.53
    دانشنامهٔ
    -0.52
     orec
    -0.49
     suporta
    -0.48
    ніципа
    -0.47
    POSITIVE LOGITS
     USP
    3.14
    USP
    1.98
    허
    1.85
    原始内容存档于
    1.09
    usp
    0.99
    出版年
    0.79
    참고
    0.77
     оригіналу
    0.72
    })));
    0.68
    GEBURTSDATUM
    0.68
    Activations Density 0.008%

    No Known Activations