© 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. 6966
    Prev
    Next
    INDEX
    Explanations

    specific legal or technical terms related to judicial proceedings and evaluations

    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
    jojo
    -0.42
    Dabei
    -0.41
    desertcart
    -0.38
    denza
    -0.38
    isti
    -0.37
    ристання
    -0.36
    iotti
    -0.36
     devastated
    -0.36
     pula
    -0.36
    chevrolet
    -0.36
    POSITIVE LOGITS
    цездатний
    0.79
    AddTagHelper
    0.71
     resourceCulture
    0.61
    bootstrapcdn
    0.60
    webElementXpaths
    0.57
     AssemblyCulture
    0.56
    tagHelperRunner
    0.54
    RegressionTest
    0.52
    waitKey
    0.50
    TargetException
    0.50
    Activations Density 0.169%

    No Known Activations