© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5303
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal and judicial proceedings

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

    that come after "of" or "than"

    np_acts-logits-general · gemini-2.0-flash

    fiction, religion, fable, opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     sufferings
    -0.52
     viewDidLoad
    -0.52
     researches
    -0.50
     ComVisible
    -0.49
     trainings
    -0.48
    FunctionFlags
    -0.48
    Viitteet
    -0.47
     useAppContext
    -0.46
    下载附件
    -0.46
    specialchars
    -0.46
    POSITIVE LOGITS
     detail
    0.85
     opportunity
    0.82
     circumstance
    0.79
     opinion
    0.72
     observation
    0.70
     inquiry
    0.70
     endeavor
    0.70
     expression
    0.69
     endeavour
    0.67
    queryInterface
    0.66
    Activations Density 0.657%

    No Known Activations