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. 2-GEMMASCOPE-RES-16K
    6. 6792
    Prev
    Next
    INDEX
    Explanations

    references to a deity or higher power, specifically the term "Lord."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.74
    +#+#
    -0.67
    :].
    -0.63
     hindurch
    -0.62
    :],
    -0.60
    tagHelperRunner
    -0.59
    ьаж
    -0.57
    ']}
    -0.56
    ibra
    -0.56
    "]}
    -0.56
    POSITIVE LOGITS
     Lord
    3.29
    Lord
    3.02
     lord
    2.71
     LORD
    2.69
    LORD
    2.31
    lord
    2.18
     Lords
    2.06
     lords
    1.96
     Seigneur
    1.63
     Senhor
    1.47
    Activations Density 0.105%

    No Known Activations