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. 11-GEMMASCOPE-RES-16K
    6. 5952
    Prev
    Next
    INDEX
    Explanations

    phrases that express conditions or qualifications, often using "while" or "although."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::_('
    -0.71
     AssemblyCulture
    -0.70
     disponibilités
    -0.66
    zeba
    -0.63
    انتهای
    -0.63
    érez
    -0.62
     pungkasnya
    -0.60
    efeated
    -0.60
    Marcia
    -0.59
    boneca
    -0.59
    POSITIVE LOGITS
    Though
    0.94
     Though
    0.86
    Although
    0.84
    though
    0.79
     though
    0.78
     Although
    0.77
    While
    0.77
     '',
    
    0.74
     While
    0.72
     "",
    
    0.72
    Activations Density 0.128%

    No Known Activations