© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15942
    Prev
    Next
    INDEX
    Explanations

    interactions and descriptions related to events and personal experiences

    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
     surla
    -0.68
    bootstrapcdn
    -0.67
     Taktlose
    -0.54
     Houſe
    -0.54
    ſelves
    -0.54
    ſelf
    -0.53
    migrationBuilder
    -0.52
     itſelf
    -0.51
     seorang
    -0.49
    Datuak
    -0.47
    POSITIVE LOGITS
     constantly
    0.66
     repeatedly
    0.61
     constantemente
    0.60
     continually
    0.55
    不断
    0.54
    不斷
    0.52
     continuously
    0.51
     continuamente
    0.49
     incessantly
    0.48
    たびに
    0.48
    Activations Density 0.504%

    No Known Activations