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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73734
    Prev
    Next
    INDEX
    Explanations

    concepts and themes surrounding human life and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    parsedMessage
    -0.67
     spéciaux
    -0.59
     CreateTagHelper
    -0.58
     مرئيه
    -0.57
     conosce
    -0.56
    帖最后由
    -0.56
    OGND
    -0.54
     boneca
    -0.52
    kmale
    -0.52
     fédé
    -0.51
    POSITIVE LOGITS
    SharedCtor
    0.38
     lifestyle
    0.38
    ArrowToggle
    0.37
    verwijspagina
    0.37
    WE
    0.36
     utafitiHapana
    0.36
    adj
    0.36
     Lebens
    0.35
     life
    0.35
    UnsafeEnabled
    0.33
    Activations Density 0.055%

    No Known Activations