© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    comments and documentation within code

    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
    出版年
    -0.61
     orth
    -0.47
    Organisateur
    -0.46
    principalTable
    -0.45
     الرياضيه
    -0.45
    Viitteet
    -0.44
    __":
    -0.43
     ze
    -0.42
    !*\
    -0.41
     CIA
    -0.41
    POSITIVE LOGITS
     defaultstate
    0.58
    exitRule
    0.50
    adaptiveStyles
    0.48
    inSlope
    0.46
    pantalones
    0.45
     Füßen
    0.42
    <!--
    0.42
    +//
    0.41
    //
    0.41
    énario
    0.41
    Activations Density 0.166%

    No Known Activations