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. 20-GEMMASCOPE-RES-16K
    6. 11212
    Prev
    Next
    INDEX
    Explanations

    terms related to towing vehicles and their functions

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

    Transportation of items or people

    np_acts-logits-general · gemini-2.0-flash

    moving vehicles or cargo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mtrl
    -0.55
     espada
    -0.48
     relógio
    -0.47
     Topology
    -0.46
    Fle
    -0.45
     pocket
    -0.44
    fusion
    -0.43
     становника
    -0.43
    lyl
    -0.43
     посе
    -0.43
    POSITIVE LOGITS
     towed
    1.08
     wheeled
    1.00
     dolly
    1.00
     towing
    0.98
     transported
    0.94
     transporting
    0.91
     lift
    0.91
     Towing
    0.91
     loading
    0.91
     trailer
    0.91
    Activations Density 0.276%

    No Known Activations