© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11063
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to programming structures, particularly in the context of databases and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.52
     nahilalakip
    -0.51
    UrlResolution
    -0.48
    httphttps
    -0.46
     zijne
    -0.46
     pungkas
    -0.44
     Demokratie
    -0.44
     régulière
    -0.43
    kijken
    -0.42
    期刊论文
    -0.41
    POSITIVE LOGITS
     Meksiku
    0.63
    IVEREF
    0.49
    WebControls
    0.46
    thâu
    0.46
     oprot
    0.45
    BSITE
    0.45
    出版年
    0.43
    igua
    0.43
    Ӕ
    0.43
     noDo
    0.42
    Activations Density 0.634%

    No Known Activations