© 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. 20-GEMMASCOPE-RES-16K
    11. 884
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing processes and materials

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

    Steel and metal materials

    np_acts-logits-general · gemini-2.0-flash

    rolled steel and metal parts

    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
     peat
    -0.61
     kasarigan
    -0.61
    Orchid
    -0.54
     Peat
    -0.51
     grooming
    -0.50
    Földrajzportál
    -0.48
     secar
    -0.48
    formatics
    -0.48
    추
    -0.48
    sandal
    -0.48
    POSITIVE LOGITS
     steel
    1.53
     metal
    1.41
     Steel
    1.30
    steel
    1.25
     iron
    1.23
    Steel
    1.23
     STEEL
    1.20
     Metal
    1.19
    metal
    1.16
    Metal
    1.14
    Activations Density 0.333%

    No Known Activations