© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6564
    Prev
    Next
    INDEX
    Explanations

    manufacturing and processing methods related to metals and materials

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

    Metal alloys and metallurgy

    np_acts-logits-general · gemini-2.0-flash

    drawing metals rolled

    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
     kasarigan
    -0.77
     peat
    -0.56
    roek
    -0.54
     Dried
    -0.53
     dries
    -0.51
     Peat
    -0.50
     sticky
    -0.49
    moist
    -0.49
    rientes
    -0.49
    transpiration
    -0.48
    POSITIVE LOGITS
     alloy
    1.13
     Alloy
    1.01
     alloys
    0.91
    Alloy
    0.91
    alloy
    0.90
     metal
    0.86
     Alloys
    0.84
     metallurgy
    0.83
     weld
    0.82
     metall
    0.80
    Activations Density 0.379%

    No Known Activations