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. 2480
    Prev
    Next
    INDEX
    Explanations

    conjugated forms of the verb "realize" and related expressions

    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
    
    -0.65
     bomb
    -0.63
    لاثة
    -0.62
     ویکی‌پدیای
    -0.61
    cotch
    -0.61
    Pozdrawiam
    -0.60
    баты
    -0.59
    readFileSync
    -0.59
    StructEnd
    -0.58
     Pand
    -0.58
    POSITIVE LOGITS
     realise
    2.15
     realisation
    2.14
     realize
    2.13
     realization
    2.11
     realises
    2.09
     realising
    2.07
     realizes
    2.05
     realizing
    2.03
     realised
    1.92
     realized
    1.89
    Activations Density 0.066%

    No Known Activations