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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36696
    Prev
    Next
    INDEX
    Explanations

    the word "compared" and variations of its usage in different contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Ferry
    -0.64
    i
    -0.62
    y
    -0.59
    انيف
    -0.57
    ífica
    -0.56
    ならない
    -0.54
    sterious
    -0.54
    Rite
    -0.53
    iffy
    -0.53
    ي
    -0.53
    POSITIVE LOGITS
    Compared
    1.05
     Compared
    1.05
     compared
    1.04
    compared
    1.01
     rispetto
    0.88
     Мексичка
    0.85
    AddTagHelper
    0.75
     verg
    0.74
     Vgl
    0.74
    PLAC
    0.73
    Activations Density 0.025%

    No Known Activations