© 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. 3808
    Prev
    Next
    INDEX
    Explanations

    references to gold and related terms

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

    "Gold" or "golden" contexts

    np_acts-logits-general · gemini-2.0-flash

    gold or golden

    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
     IOError
    -0.47
     Fray
    -0.45
    ebab
    -0.45
    owiak
    -0.43
    fsm
    -0.42
    ▂
    -0.41
    ecki
    -0.40
    icordia
    -0.40
    دانشنامهٔ
    -0.39
    bout
    -0.39
    POSITIVE LOGITS
     gold
    1.16
    Gold
    1.15
     Gold
    1.15
     GOLD
    1.09
    GOLD
    0.99
    gold
    0.98
     Golden
    0.94
    Golden
    0.92
     Goldstein
    0.90
     GOLDEN
    0.88
    Activations Density 0.229%

    No Known Activations