© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2966
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and publications

    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
     referrerpolicy
    -0.79
    DockStyle
    -0.71
    SourceChecksum
    -0.69
    fromnode
    -0.68
    Diweddarwch
    -0.65
    Spoljašnje
    -0.63
    UnitTesting
    -0.61
    featureID
    -0.60
     חיצוניים
    -0.60
    Chham
    -0.59
    POSITIVE LOGITS
     European
    0.30
    דו
    0.29
     ред
    0.28
     investigated
    0.28
     evaluated
    0.28
     research
    0.28
    였다
    0.27
     investigate
    0.27
     report
    0.27
     Grote
    0.27
    Activations Density 0.244%

    No Known Activations