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-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 66
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative forms of the word "better" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getSystemService
    -0.52
    IRQn
    -0.51
    TargetException
    -0.51
    alakip
    -0.50
     pleaſure
    -0.49
     iſt
    -0.47
    mband
    -0.46
     JpaRepository
    -0.45
    quely
    -0.45
     typelib
    -0.45
    POSITIVE LOGITS
     sebaiknya
    0.78
    better
    0.71
     mejor
    0.71
    Better
    0.70
     better
    0.70
     conviene
    0.68
     Better
    0.67
    最好
    0.66
     лучше
    0.65
     najlepiej
    0.65
    Activations Density 0.274%

    No Known Activations