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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 74
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Her" and wireless technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.51
     CreateTagHelper
    -0.48
     rés
    -0.47
     geste
    -0.47
    ubri
    -0.46
     cell
    -0.46
    jun
    -0.45
     gagne
    -0.44
    alam
    -0.44
    Manbalar
    -0.44
    POSITIVE LOGITS
     vegan
    1.09
     Vegan
    0.99
    QMetaType
    0.90
    IndentedString
    0.86
    vegan
    0.85
    Vegan
    0.84
     vegetarian
    0.82
    ьаж
    0.79
     vegans
    0.75
    BibitemShut
    0.72
    Activations Density 0.106%

    No Known Activations