© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11529
    Prev
    Next
    INDEX
    Explanations

    connections to technical terms or libraries relevant to code snippets or programming concepts

    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
     Efq
    -1.28
     myſelf
    -1.17
     Theſe
    -1.15
     Majefty
    -1.15
     uſed
    -1.10
     pleaſure
    -1.07
     ―――――
    -1.07
     fevere
    -1.07
     itſelf
    -1.05
     Monfieur
    -1.03
    POSITIVE LOGITS
     .
    0.68
    原始内容存档于
    0.65
     Cordero
    0.64
    ambiguation
    0.63
    idigung
    0.63
    CppMethod
    0.60
     דבר
    0.58
    productList
    0.57
    薯
    0.55
    CLAIMER
    0.55
    Activations Density 0.124%

    No Known Activations