© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4391
    Prev
    Next
    INDEX
    Explanations

    content related to legal terminology and proceedings

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

    Follows "Q:" or "value" in text

    np_acts-logits-general · gemini-2.0-flash

    Q followed by colon

    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
    ,
    -0.68
     AppComponent
    -0.62
    เหร
    -0.58
     吗
    -0.56
     a
    -0.55
     end
    -0.54
     second
    -0.52
     is
    -0.52
    :
    -0.52
     for
    -0.51
    POSITIVE LOGITS
     Inſ
    0.95
     ainfi
    0.94
     AssemblyTitle
    0.92
     يتيمه
    0.92
     Reſ
    0.91
    GraphicsUnit
    0.90
     plufieurs
    0.90
     Anſ
    0.89
     auffi
    0.89
    RenderAtEndOf
    0.84
    Activations Density 0.004%

    No Known Activations