© 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. 11447
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and statutes related to claims in Mississippi

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

    Mississippi and Alabama cases

    np_acts-logits-general · gemini-2.0-flash

    mississippi and alabama court citations

    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
     createSlice
    -0.59
     dort
    -0.58
     down
    -0.55
     Administrativna
    -0.54
    Lebanon
    -0.54
     Lebanon
    -0.52
    ItemBackground
    -0.51
     мәкал
    -0.51
    itzende
    -0.50
     upstream
    -0.50
    POSITIVE LOGITS
     Mississippi
    0.78
    ValueStyle
    0.75
     Pensacola
    0.75
     Alabama
    0.70
    Mississippi
    0.66
    Alabama
    0.65
     BAH
    0.64
    WireFormatLite
    0.64
     Bahamas
    0.62
     Gulf
    0.57
    Activations Density 0.217%

    No Known Activations