© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6323
    Prev
    Next
    INDEX
    Explanations

    specific phrases that quantify rates or measurements

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

    "rate" or "rapid"

    np_acts-logits-general · gemini-2.0-flash

    rate, pace, speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     geloof
    -0.57
    webElementGuid
    -0.48
     zru
    -0.44
     AppCompatTheme
    -0.44
     artística
    -0.44
    hésite
    -0.43
     keuze
    -0.43
    CppCodeGen
    -0.43
    Према
    -0.43
     ficam
    -0.42
    POSITIVE LOGITS
     rate
    1.01
    Rate
    0.91
     Rate
    0.91
     pace
    0.88
    rate
    0.83
     RATE
    0.80
     speed
    0.80
     rapid
    0.75
     faster
    0.73
     speeds
    0.71
    Activations Density 0.732%

    No Known Activations