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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15551
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "re-", indicating repetition or restoration actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CGSize
    -0.50
     ब्रेकडाउन
    -0.49
    oredCriteria
    -0.42
     للمعارف
    -0.42
    ěte
    -0.40
    borderSide
    -0.40
    Additive
    -0.40
    LLocation
    -0.39
     Domain
    -0.39
     فار
    -0.39
    POSITIVE LOGITS
     yeniden
    1.03
     rebuild
    0.91
     restart
    0.91
     rebuilding
    0.90
    重新
    0.90
     re
    0.90
     újra
    0.88
     rebuilt
    0.86
    rebuild
    0.86
     recast
    0.85
    Activations Density 0.484%

    No Known Activations