© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    instances of code related to API operations and data handling

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

    Code editing operations

    np_acts-logits-general · gemini-2.0-flash

    CRUD operations (create, read, update, delete)

    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
    expandindo
    -0.62
    Diwedd
    -0.62
    IContainer
    -0.59
    الدراسه
    -0.59
     BoxDecoration
    -0.55
    Morfologia
    -0.53
     communiquez
    -0.52
    Дереккөздер
    -0.50
    AddTagHelper
    -0.50
    //
    -0.49
    POSITIVE LOGITS
     edit
    1.02
     delete
    0.99
     Edit
    0.96
     save
    0.88
    delete
    0.87
    edit
    0.84
    Edit
    0.84
     update
    0.82
     Delete
    0.82
     insert
    0.80
    Activations Density 0.395%

    No Known Activations