Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2999
    Prev
    Next
    INDEX
    Explanations

    HTML and XML tags, focusing on their attributes and closing elements

    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
    ($("#
    -0.63
    Nuorodos
    -0.57
    ợp
    -0.53
     Bele
    -0.53
     personalities
    -0.53
     voud
    -0.51
     disc
    -0.51
     sposob
    -0.51
     トート
    -0.50
     personalidad
    -0.50
    POSITIVE LOGITS
     يتيمه
    0.97
    WriteTagHelper
    0.89
    ArgsConstructor
    0.88
     utafitiHapana
    0.82
    ///</
    0.77
    ContentAsync
    0.76
     للاسماء
    0.75
    DoubleQuotes
    0.73
    الدراسه
    0.72
     وتسجيلات
    0.71
    Activations Density 0.132%

    No Known Activations