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. 1849
    Prev
    Next
    INDEX
    Explanations

    phrases related to software installation and configuration issues

    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
     sánchez
    -0.73
     mijne
    -0.65
     rodríguez
    -0.64
     aveug
    -0.63
     ш
    -0.61
     jesús
    -0.60
     venons
    -0.59
     löyty
    -0.59
     “¿
    -0.59
    ス
    -0.59
    POSITIVE LOGITS
     LoginPage
    0.88
    PositiveButton
    0.88
     تانيه
    0.84
    Filmographie
    0.84
     Designers
    0.79
     DbContext
    0.78
    StoreMessageInfo
    0.78
     bacterias
    0.77
     therefrom
    0.76
     Fonda
    0.76
    Activations Density 0.098%

    No Known Activations