© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15070
    Prev
    Next
    INDEX
    Explanations

    concepts related to crime, law, and societal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.59
     ***!
    -0.57
    oneofs
    -0.57
     smtplib
    -0.56
     nonUne
    -0.56
     Defects
    -0.54
    adpleegd
    -0.52
    __*/
    -0.52
    AnimationsModule
    -0.52
     дописавши
    -0.51
    POSITIVE LOGITS
     interactions
    0.57
     relationships
    0.55
     influencing
    0.54
     interaction
    0.53
     interact
    0.53
     influences
    0.51
     people
    0.48
     influence
    0.47
     social
    0.47
     determining
    0.46
    Activations Density 0.387%

    No Known Activations