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. 44099
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "import" related to programming modules or libraries

    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
     Taktlose
    -0.60
     surla
    -0.59
    RenderAtEndOf
    -0.58
     springfox
    -0.54
     beginnetje
    -0.54
    addGap
    -0.51
     CreateTagHelper
    -0.51
    ſelf
    -0.51
    addContainerGap
    -0.49
     faſt
    -0.48
    POSITIVE LOGITS
    import
    0.56
     lateinit
    0.47
     tink
    0.46
    SKIP
    0.46
     mừng
    0.45
     Honig
    0.43
     erlaubt
    0.43
     kotlinx
    0.43
    sau
    0.43
    using
    0.43
    Activations Density 0.001%

    No Known Activations