Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8408
    Prev
    Next
    INDEX
    Explanations

    references to gold and silver

    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
    /*
    -0.83
    клопе
    -0.74
    __["
    -0.70
    ---*/
    -0.67
    __':
    
    -0.65
    voces
    -0.63
    ../../
    -0.62
     Muses
    -0.62
    __(/*!
    -0.62
    rég
    -0.60
    POSITIVE LOGITS
     Gold
    3.26
     gold
    3.24
    Gold
    3.09
    gold
    2.97
     GOLD
    2.89
    GOLD
    2.56
    ゴールド
    1.85
     golden
    1.84
    golden
    1.76
     золота
    1.74
    Activations Density 0.042%

    No Known Activations