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. 13268
    Prev
    Next
    INDEX
    Explanations

    instances of the word "own."

    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
     vectorielle
    -0.69
     touristique
    -0.66
    er
    -0.65
     vectorielles
    -0.65
     énergé
    -0.63
     novità
    -0.62
     annonce
    -0.59
    ically
    -0.59
     religieuses
    -0.59
     lumineux
    -0.59
    POSITIVE LOGITS
     own
    2.00
     Own
    1.74
    Own
    1.63
     OWN
    1.61
    own
    1.52
     eigenen
    1.33
     sendiri
    1.20
     соб
    1.19
    OWN
    1.18
     eigenes
    1.16
    Activations Density 0.061%

    No Known Activations