© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2428
    Prev
    Next
    INDEX
    Explanations

    units of measurement and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.82
     desmotivaciones
    -0.74
     määrä
    -0.70
     âmes
    -0.69
     Gegenteil
    -0.67
     féminine
    -0.66
     Grüsse
    -0.66
     ympä
    -0.66
     borboleta
    -0.65
     meille
    -0.63
    POSITIVE LOGITS
     kg
    1.20
     km
    1.14
     cm
    1.05
     mL
    0.96
     mm
    0.91
     oz
    0.89
     kW
    0.86
     kJ
    0.86
     Hz
    0.85
     lbs
    0.84
    Activations Density 0.626%

    No Known Activations