© 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. 31-GEMMASCOPE-RES-16K
    11. 14106
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fast" and related terms or concepts

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

    the phrase "fast forward" used as a temporal transition.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.46
     zelve
    -0.45
     consciência
    -0.44
     vectorielles
    -0.42
     realização
    -0.41
    rungsseite
    -0.41
     Leinwand
    -0.41
     Jurí
    -0.41
     ilusión
    -0.40
    miento
    -0.40
    POSITIVE LOGITS
     Fast
    0.98
    Fast
    0.90
     fast
    0.86
     FAST
    0.81
    fast
    0.80
    FAST
    0.73
    Fas
    0.70
     Fas
    0.68
     FAS
    0.64
     fas
    0.63
    Activations Density 0.052%

    No Known Activations