© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4402
    Prev
    Next
    INDEX
    Explanations

    actions related to riding or operating vehicles, particularly motorcycles

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

    "riding", "ride", or "rode"

    np_acts-logits-general · gemini-2.0-flash

    riding the wave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.67
    jface
    -0.54
    hafen
    -0.52
    hwar
    -0.52
     Campo
    -0.50
    \{\\
    -0.48
     Gaze
    -0.47
    〖
    -0.46
    کور
    -0.45
    ecake
    -0.45
    POSITIVE LOGITS
     rides
    1.62
     riding
    1.48
     ride
    1.47
     riders
    1.46
     rode
    1.45
     Rides
    1.40
     Riding
    1.39
     rider
    1.38
     RIDE
    1.34
     Ride
    1.33
    Activations Density 0.083%

    No Known Activations