© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4437
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court rulings

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

    "Colo" abbreviation followed by a period

    np_acts-logits-general · gemini-2.0-flash

    Colorado and Tenth Circuit legal cases

    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
    oredCriteria
    -0.68
    ᅠ
    -0.68
     onPostExecute
    -0.66
    StructEnd
    -0.63
    galus
    -0.63
     Orkney
    -0.62
    httphttps
    -0.61
    twimg
    -0.60
    таратура
    -0.59
     GenerationType
    -0.59
    POSITIVE LOGITS
     Mexique
    0.41
    CodedInputStream
    0.40
    mybatisplus
    0.39
    marginHorizontal
    0.39
     Broncos
    0.37
     Colorado
    0.35
     Orange
    0.34
     Tulsa
    0.33
    utul
    0.33
     COLORADO
    0.33
    Activations Density 0.709%

    No Known Activations