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. 12-GEMMASCOPE-RES-16K
    6. 1628
    Prev
    Next
    INDEX
    Explanations

    prepositions and connectors that indicate relationships between elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.72
     Majefty
    -0.70
    جستارهای
    -0.69
     Gött
    -0.69
     itſelf
    -0.68
     Paese
    -0.68
    ıyors
    -0.65
    ity
    -0.65
     adic
    -0.64
     ++)
    -0.64
    POSITIVE LOGITS
     za
    0.84
     за
    0.81
    parsedMessage
    0.79
    GEBURTSDATUM
    0.78
    За
    0.77
    К
    0.75
    ]='\
    0.74
     colorWith
    0.73
     з
    0.72
    ManagedBean
    0.72
    Activations Density 0.028%

    No Known Activations