© 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. 21-GEMMASCOPE-RES-16K
    6. 11003
    Prev
    Next
    INDEX
    Explanations

    specific structures or formal elements in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.32
     sen
    -0.31
    ost
    -0.31
     ждут
    -0.30
     diser
    -0.30
     known
    -0.29
     os
    -0.28
     nar
    -0.28
     ob
    -0.28
     fla
    -0.28
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    AsUp
    0.64
     betweenstory
    0.63
    setupUi
    0.62
     становника
    0.59
    enderror
    0.57
     للاسماء
    0.57
    UnusedPrivate
    0.57
    MigrationBuilder
    0.56
    CppCodeGen
    0.56
    Activations Density 1.311%

    No Known Activations