© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 12323
    Prev
    Next
    INDEX
    Explanations

    code-related elements and operations involving databases, particularly CRUD (Create, Read, Update, Delete) operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -0.51
    /*
    -0.50
    now
    -0.46
     run
    -0.44
    iena
    -0.44
     Pap
    -0.43
     Sug
    -0.43
    iane
    -0.43
    +}\
    -0.42
    吧
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.80
    ViewFeatures
    0.78
    principalColumn
    0.77
    CloseOperation
    0.72
    Identified
    0.69
     NSCoder
    0.69
     useParams
    0.68
    PreferredItem
    0.67
     themſelves
    0.67
    :✨
    0.66
    Activations Density 0.347%

    No Known Activations