© 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. 9-GEMMASCOPE-RES-16K
    11. 9014
    Prev
    Next
    INDEX
    Explanations

    terms related to speed, efficiency, and acceleration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to increasing speed or acceleration, often using terms like "speed up", "quick way", or "accelerate".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.45
    CppMethod
    -0.43
     незавершена
    -0.43
    seteq
    -0.42
    ///</
    -0.37
    ScopeManager
    -0.37
    URIComponent
    -0.37
    UnitTesting
    -0.36
     gracious
    -0.36
    ficulty
    -0.35
    POSITIVE LOGITS
     fast
    1.34
     Fast
    1.24
     faster
    1.23
     quick
    1.23
    quick
    1.23
    fast
    1.23
     fastest
    1.23
     Faster
    1.20
     speedy
    1.20
    Fast
    1.19
    Activations Density 0.620%

    No Known Activations