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. 36615
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to experiments and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    MessageTagHelper
    -0.70
    Enllaces
    -0.50
    脚注の使い方
    -0.50
    RTEE
    -0.49
     odkazy
    -0.48
    RectangleBorder
    -0.46
    ViewImports
    -0.45
    ronpa
    -0.45
     cucchiai
    -0.45
    argout
    -0.44
    POSITIVE LOGITS
     pinulongan
    0.42
     '{@
    0.37
    Билгалдахарш
    0.37
    듯
    0.34
     MainAxisSize
    0.34
    nave
    0.34
    HomeAsUp
    0.34
    Према
    0.34
    endregion
    0.33
     yyr
    0.32
    Activations Density 0.429%

    No Known Activations