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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3757
    Prev
    Next
    INDEX
    Explanations

    emotions and physical sensations associated with discomfort and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    งาม
    -0.52
    FormTagHelper
    -0.51
    anovich
    -0.48
     AssemblyProduct
    -0.46
    scala
    -0.46
    laire
    -0.45
    ègre
    -0.44
    かわらず
    -0.44
    itania
    -0.43
     règle
    -0.43
    POSITIVE LOGITS
    ContentAsync
    0.66
    InSection
    0.65
    DispatchToProps
    0.64
     Slee
    0.57
     nuns
    0.56
     mapStateToProps
    0.56
    存于互联网档案馆
    0.55
    ";}
    0.55
     fometimes
    0.55
     Efq
    0.55
    Activations Density 0.479%

    No Known Activations