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. 11-GEMMASCOPE-RES-16K
    6. 7000
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or qualifications, particularly focusing on the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ftate
    -0.64
     preuves
    -0.63
     stället
    -0.62
     Chriftian
    -0.62
     Libya
    -0.60
     fubject
    -0.60
     ſtate
    -0.60
     Chrift
    -0.60
    Libya
    -0.59
     vektör
    -0.58
    POSITIVE LOGITS
    sowie
    0.99
     other
    0.94
    mybatisplus
    0.93
    apimachinery
    0.91
     unknownFields
    0.88
    PerformLayout
    0.85
    HasAnnotation
    0.83
     וגם
    0.83
    NameInMap
    0.83
     виправивши
    0.81
    Activations Density 0.087%

    No Known Activations