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. 62192
    Prev
    Next
    INDEX
    Explanations

    identifiers and elements related to programming interfaces and structures

    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
     <>",
    -0.60
    enterOuterAlt
    -0.57
    发表于
    -0.54
     comuniques
    -0.54
    󠁣
    -0.50
     estekak
    -0.49
    ➟
    -0.46
    .*")]
    -0.46
    LabelTagHelper
    -0.46
    OuterAlt
    -0.46
    POSITIVE LOGITS
     ahor
    0.42
    MENAFN
    0.38
     mères
    0.36
    беріга
    0.35
     térmica
    0.35
     africains
    0.35
     latter
    0.35
     języka
    0.34
     BrowserModule
    0.34
     mentira
    0.34
    Activations Density 0.000%

    No Known Activations