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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 69544
    Prev
    Next
    INDEX
    Explanations

    keywords and functions related to saving and managing posts in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antwort
    -0.32
    doGet
    -0.31
    ListFragment
    -0.27
     gouvern
    -0.26
    ゾート
    -0.26
     asociados
    -0.26
     missp
    -0.25
    くな
    -0.24
     iç
    -0.24
    ddot
    -0.24
    POSITIVE LOGITS
     kasarigan
    0.89
    RegressionTest
    0.76
    RenderAtEndOf
    0.75
     snippetHide
    0.69
    出版年
    0.69
    HtmlAttribute
    0.68
    AndEndTag
    0.67
    Personendaten
    0.66
    httphttps
    0.65
     otomatig
    0.63
    Activations Density 0.006%

    No Known Activations