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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5832
    Prev
    Next
    INDEX
    Explanations

    words ending in 'y' that describe characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptive adjectives ending in y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dům
    -0.63
    hæng
    -0.63
     vstup
    -0.60
     rozdí
    -0.60
     návště
    -0.59
     nemlig
    -0.58
     tilbud
    -0.58
     assoluto
    -0.58
    ambilan
    -0.57
     anbef
    -0.55
    POSITIVE LOGITS
    eaky
    0.72
    rusty
    0.72
    funky
    0.71
    trendy
    0.70
    y
    0.69
    dusty
    0.69
    eky
    0.68
    zzy
    0.68
    handy
    0.66
    noisy
    0.66
    Activations Density 0.027%

    No Known Activations