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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 2518
    Prev
    Next
    INDEX
    Explanations

    the word "equally" and its variations, indicating a focus on equality and balance in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.83
    PerformLayout
    -0.77
    GEBURTSDATUM
    -0.73
     BoxDecoration
    -0.65
     Rosales
    -0.61
    Wha
    -0.59
    erialized
    -0.59
    ftagPool
    -0.59
    목
    -0.58
    Evet
    -0.58
    POSITIVE LOGITS
     equally
    1.08
     Equally
    0.94
    ingly
    0.91
    >"+
    0.77
    욱
    0.76
     doubly
    0.74
     igualmente
    0.73
    theless
    0.73
    >\<^
    0.72
    ruptedException
    0.72
    Activations Density 0.155%

    No Known Activations