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. 18-GEMMASCOPE-RES-16K
    6. 10131
    Prev
    Next
    INDEX
    Explanations

    instances of the article "an" and its variations, suggesting a focus on specific noun phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muualla
    -0.78
     magasiner
    -0.74
    AsUp
    -0.73
     StatelessWidget
    -0.66
    $_['
    -0.63
     nahilalakip
    -0.63
    Sucesor
    -0.63
     الرياضيه
    -0.63
    niająca
    -0.61
     ujednoznacz
    -0.61
    POSITIVE LOGITS
     Ank
    0.81
     AN
    0.80
     An
    0.76
     Ans
    0.76
    An
    0.66
     Anz
    0.63
     ans
    0.61
    AN
    0.60
     ANS
    0.57
    ank
    0.57
    Activations Density 0.199%

    No Known Activations