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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 13499
    Prev
    Next
    INDEX
    Explanations

    terms related to database operations, specifically deletion and management of entries

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

    deleting or removing

    np_acts-logits-general · gemini-2.0-flash

    delete or remove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.68
     estimés
    -0.62
    styleType
    -0.59
    jsonwebtoken
    -0.54
    RLock
    -0.53
    PyExc
    -0.52
    Izvori
    -0.50
    ContentAsync
    -0.49
     diversification
    -0.47
    LookAnd
    -0.47
    POSITIVE LOGITS
     delete
    2.54
     deletion
    2.34
     deleting
    2.33
     Delete
    2.27
    delete
    2.27
     deleted
    2.24
     removal
    2.24
    Delete
    2.13
     deletes
    2.13
     remove
    2.05
    Activations Density 0.578%

    No Known Activations