© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3675
    Prev
    Next
    INDEX
    Explanations

    references to character development and production details in film and television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "how" (in multiple languages)

    np_acts-logits-general · gemini-2.0-flash

    how things happen or change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     الحره
    -0.80
    aarrggbb
    -0.75
    WriteTagHelper
    -0.74
    ſam
    -0.70
    iſen
    -0.65
    linawan
    -0.65
     CreateTagHelper
    -0.65
    niſſe
    -0.61
    ſchen
    -0.60
    <unused41>
    -0.60
    POSITIVE LOGITS
     how
    0.38
     cómo
    0.38
     Cómo
    0.35
     How
    0.33
    どのように
    0.31
     hogyan
    0.30
     serem
    0.30
    บ้าง
    0.29
     nasıl
    0.29
    How
    0.29
    Activations Density 1.042%

    No Known Activations