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. 18-GEMMASCOPE-RES-16K
    6. 2291
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to appeals and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References, footnotes, and notes

    np_acts-logits-general · gemini-2.0-flash

    Legal and academic referencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     L
    -0.53
    omitempty
    -0.51
     Chwiliwch
    -0.49
     D
    -0.48
    ench
    -0.47
     Is
    -0.47
     <>",
    -0.47
     Ra
    -0.47
     Official
    -0.46
    iki
    -0.45
    POSITIVE LOGITS
    FOOTNOTES
    0.91
    ${
    0.85
    Footnotes
    0.81
     дописавши
    0.80
     Footnote
    0.78
    AnchorStyles
    0.77
     footnotes
    0.76
    
    0.75
     footnote
    0.70
    脚注の使い方
    0.69
    Activations Density 0.144%

    No Known Activations