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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14836
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to court cases

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

    Legal citations and references to Alabama

    np_acts-logits-general · gemini-2.0-flash

    US Southern states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.34
    Przypisy
    -0.33
     surla
    -0.32
     Kesehatan
    -0.31
    glfw
    -0.31
     Canadian
    -0.31
     Kanada
    -0.29
     îng
    -0.28
    adpleegd
    -0.28
     zg
    -0.27
    POSITIVE LOGITS
     Alabama
    0.94
    Alabama
    0.90
    caloosa
    0.85
     otomatig
    0.80
     Tennessee
    0.80
    Tennessee
    0.77
     Mississippi
    0.76
    Atlanta
    0.76
    Louisiana
    0.76
     Arkansas
    0.76
    Activations Density 0.764%

    No Known Activations