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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1766
    Prev
    Next
    INDEX
    Explanations

    financial or economic numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    Hauptartikel
    -0.79
     Wiktionnaire
    -0.69
    ]='\
    -0.68
    DoubleQuotes
    -0.65
     Waray
    -0.65
     propOrder
    -0.65
    thâu
    -0.63
     Baillargeon
    -0.61
    VersionUID
    -0.59
    ]))
    
    -0.59
    POSITIVE LOGITS
    +#+#
    0.73
     ride
    0.45
    сшта
    0.44
    hy
    0.44
    aktifkan
    0.44
     Ride
    0.43
     RIDE
    0.42
    PMailer
    0.42
     Вер
    0.42
    𝟸
    0.41
    Activations Density 0.243%

    No Known Activations