© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    key legal and historical terms related to cases and successes

    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
    $_['
    -0.44
     nature
    -0.39
     track
    -0.35
     natureza
    -0.34
    ItemBackground
    -0.33
     bou
    -0.32
     Beaufort
    -0.31
    照
    -0.31
     ti
    -0.31
     small
    -0.31
    POSITIVE LOGITS
     Officially
    0.57
    principalTable
    0.57
    officially
    0.57
    EDEFAULT
    0.57
     betweenstory
    0.57
    oredCriteria
    0.56
     Мексичка
    0.55
    󠁮
    0.54
    IsContent
    0.54
     officially
    0.54
    Activations Density 1.373%

    No Known Activations