© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15552
    Prev
    Next
    INDEX
    Explanations

    discussions on purpose, guidance, and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.82
    InjectAttribute
    -0.74
    StoryboardSegue
    -0.71
     ویکی‌پدی
    -0.69
    AddTagHelper
    -0.69
     Мексичка
    -0.66
     pinulongan
    -0.65
     ExecuteAsync
    -0.65
     autorytatywna
    -0.64
     JpaRepository
    -0.63
    POSITIVE LOGITS
     below
    0.45
     recent
    0.37
     some
    0.34
    below
    0.34
     Below
    0.32
     here
    0.32
     key
    0.32
     noteworthy
    0.32
    RECENT
    0.31
     prominent
    0.30
    Activations Density 0.448%

    No Known Activations