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. 2721
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "bring" and its variations

    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
     AssemblyCulture
    -0.80
     FishBase
    -0.80
    ValueStyle
    -0.78
     Rota
    -0.76
    findpost
    -0.76
     Faure
    -0.71
     EClass
    -0.70
    paravant
    -0.70
    nonatomic
    -0.70
     Myers
    -0.69
    POSITIVE LOGITS
    Bring
    2.25
     Bring
    2.17
     bring
    2.17
    Bringing
    2.09
     brought
    2.05
     Bringing
    2.04
     brings
    2.04
     bringing
    2.03
     BRING
    2.00
    bring
    1.99
    Activations Density 0.031%

    No Known Activations