© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6347
    Prev
    Next
    INDEX
    Explanations

    references to the term "golden" in various contexts or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyasha
    -0.72
    umball
    -0.68
     McCulloch
    -0.63
    groep
    -0.62
    kheim
    -0.61
    DataMember
    -0.60
    łość
    -0.60
    RadioGroup
    -0.59
     Họ
    -0.59
     Marcy
    -0.59
    POSITIVE LOGITS
     Golden
    3.04
    Golden
    2.88
     golden
    2.65
    golden
    2.61
     GOLDEN
    2.56
    ゴールデン
    1.28
     Золо
    1.21
    黄金
    1.13
    Золо
    1.11
     dorada
    1.05
    Activations Density 0.052%

    No Known Activations