© 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. 33-GEMMASCOPE-RES-16K
    11. 12190
    Prev
    Next
    INDEX
    Explanations

    terms related to speed and pacing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölkerung
    -0.36
     NSCoder
    -0.35
     doccia
    -0.34
    해
    -0.32
     bocca
    -0.32
     parkir
    -0.29
    ांक
    -0.29
     frutta
    -0.29
    droje
    -0.29
     görüş
    -0.29
    POSITIVE LOGITS
     pace
    2.36
     ritmo
    1.99
     rhythm
    1.88
     Pace
    1.85
    Pace
    1.84
     tempo
    1.81
     rythme
    1.81
     pacing
    1.66
    rhythm
    1.61
     rhythms
    1.58
    Activations Density 0.254%

    No Known Activations