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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7511
    Prev
    Next
    INDEX
    Explanations

    the structure of written content, focusing on formatting elements and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     pleaſure
    -0.74
    出版年
    -0.73
     houſe
    -0.66
    richTextPanel
    -0.65
     ſtate
    -0.63
     ſal
    -0.60
    parsedMessage
    -0.60
    ſelves
    -0.59
     Anſ
    -0.59
     ſche
    -0.59
    POSITIVE LOGITS
    :✨
    0.43
    Географиясе
    0.41
    SystemColors
    0.41
    FormTagHelper
    0.39
    mic
    0.35
    yntaxException
    0.35
    PropertyChanged
    0.34
     чого
    0.33
     AssemblyTitle
    0.33
    phosa
    0.33
    Activations Density 0.895%

    No Known Activations