© 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. 12411
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and confidentiality in health information

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

    Followed by "user" or related to data usage

    np_acts-logits-general · gemini-2.0-flash

    data privacy and usage

    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
     Gruber
    -0.44
     Deep
    -0.43
     Herzog
    -0.43
     Kraw
    -0.42
     extreme
    -0.42
    Deep
    -0.42
    AP
    -0.42
    Groß
    -0.41
     deep
    -0.40
     AP
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.52
    InjectAttribute
    0.52
     <<<<<<<<<<<<<<
    0.50
     nahilalakip
    0.48
    
    0.47
     SwitchCompat
    0.46
    AsUp
    0.45
     للاسماء
    0.45
     ModelExpression
    0.45
     كومونز
    0.44
    Activations Density 0.168%

    No Known Activations