Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8287
    Prev
    Next
    INDEX
    Explanations

    information related to motorcycle specifications and pricing

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

    Motorcycles or motorcycle riding

    np_acts-logits-general · gemini-2.0-flash

    motorcycle and bike adventure

    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
    setVerticalGroup
    -0.75
    tagHelperRunner
    -0.55
     zwem
    -0.55
    asantry
    -0.55
    SequentialGroup
    -0.51
    toHaveBeenCalled
    -0.51
    avut
    -0.49
     Curling
    -0.49
     Fenster
    -0.48
    fifa
    -0.48
    POSITIVE LOGITS
     motorcycle
    1.21
     motorcycles
    1.08
     Motorcycle
    1.05
     riders
    1.00
    Motorcycle
    1.00
     motorbike
    0.94
     rider
    0.93
     bike
    0.92
     motocic
    0.91
    motorcycle
    0.90
    Activations Density 0.091%

    No Known Activations