© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12663
    Prev
    Next
    INDEX
    Explanations

    references to libraries and their associated services or collections

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

    libraries or databases

    np_acts-logits-general · gemini-2.0-flash

    library and collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    bootstrapcdn
    -0.67
     ExecuteAsync
    -0.64
    styleable
    -0.57
     HasFactory
    -0.56
    complexContent
    -0.55
     createState
    -0.54
    IsContent
    -0.52
    şört
    -0.52
    DebuggerNonUser
    -0.52
    saraba
    -0.50
    POSITIVE LOGITS
     librarian
    0.80
     librarians
    0.77
     library
    0.67
     Librarian
    0.66
     Library
    0.59
    Libr
    0.58
     Librarians
    0.54
    Library
    0.52
     Bibliote
    0.52
     libraries
    0.51
    Activations Density 0.101%

    No Known Activations