© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 12458
    Prev
    Next
    INDEX
    Explanations

    references to gold and its associations, including terms related to quantities and contexts in which gold is significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mListener
    -0.76
    uyasha
    -0.75
    adaptiveStyles
    -0.73
     compri
    -0.72
     propOrder
    -0.72
    клопе
    -0.71
    osoba
    -0.70
     Arjuna
    -0.69
     Dishwasher
    -0.69
    uyện
    -0.68
    POSITIVE LOGITS
     Gold
    1.86
     gold
    1.84
    Gold
    1.74
     GOLD
    1.71
    gold
    1.68
    GOLD
    1.49
     golden
    1.30
    golden
    1.29
     Goldstein
    1.23
     Golden
    1.20
    Activations Density 0.058%

    No Known Activations