© 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. 15488
    Prev
    Next
    INDEX
    Explanations

    references to professional medical or technical services and institutions

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

    Tools, equipment, or processes

    np_acts-logits-general · gemini-2.0-flash

    equip yourself with

    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
    DeleteBehavior
    -0.63
     élevées
    -0.55
    出版年
    -0.51
    IVEREF
    -0.50
     HttpNotFound
    -0.48
    atschapp
    -0.47
     ouvertes
    -0.47
     pasaj
    -0.46
    ScopeManager
    -0.46
    ########.
    -0.46
    POSITIVE LOGITS
     equipment
    2.13
    equipment
    1.80
     Equipment
    1.79
     equipments
    1.77
    Equipment
    1.69
     EQUIPMENT
    1.67
     tools
    1.58
    EQUIPMENT
    1.56
     equip
    1.54
     Equip
    1.46
    Activations Density 0.355%

    No Known Activations