© 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. 10-GEMMASCOPE-RES-16K
    11. 4786
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing processes and materials in engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.59
    borderTop
    -0.56
    antd
    -0.54
     auctor
    -0.54
    Puss
    -0.52
    ValueStyle
    -0.49
     shingle
    -0.49
     phân
    -0.48
     agency
    -0.48
     ratified
    -0.47
    POSITIVE LOGITS
     moulds
    0.73
     molds
    0.73
     mold
    0.72
     sculpt
    0.72
    MLLoader
    0.71
     molding
    0.69
    stø
    0.69
     mould
    0.66
     shapes
    0.65
     moulding
    0.65
    Activations Density 0.387%

    No Known Activations