© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15115
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing processes

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

    Numbers in figures

    np_acts-logits-general · gemini-2.0-flash

    numbers and component labels

    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
    -0.79
    PerformLayout
    -0.79
     дописавши
    -0.75
    MethodManager
    -0.73
     مشين
    -0.70
    ftagPool
    -0.69
     незавершена
    -0.69
    Portale
    -0.68
     gloire
    -0.67
    цездатний
    -0.67
    POSITIVE LOGITS
     suffix
    0.50
    1
    0.48
    ecore
    0.47
     Byz
    0.46
     prefix
    0.45
     Byzantine
    0.45
    2
    0.44
    /
    0.44
    8
    0.43
     eingesetzt
    0.41
    Activations Density 0.823%

    No Known Activations