© 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. 20-GEMMASCOPE-RES-16K
    11. 13917
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.44
     Deshalb
    -0.43
     murni
    -0.42
    endregion
    -0.41
    enumi
    -0.41
    ParallelGroup
    -0.40
     contigo
    -0.40
    routeProvider
    -0.39
    Cubit
    -0.39
    esistenza
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.62
    arangay
    0.57
     JADX
    0.57
    hematical
    0.55
     Janata
    0.52
     nakalista
    0.51
     IBRARY
    0.49
    iffance
    0.48
    Diwedd
    0.46
     Dolce
    0.46
    Activations Density 0.501%

    No Known Activations