© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7858
    Prev
    Next
    INDEX
    Explanations

    contexts related to control and societal dynamics

    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
     packages
    -0.31
     pozycji
    -0.29
     majors
    -0.29
     Berufs
    -0.29
     arrangement
    -0.29
     station
    -0.28
     Major
    -0.27
     positions
    -0.27
     linguagem
    -0.27
     position
    -0.27
    POSITIVE LOGITS
     ModelExpression
    0.80
    writeFieldEnd
    0.79
     '\\;'
    0.75
    ValueStyle
    0.69
    MessageOf
    0.68
    parsedMessage
    0.68
     مشين
    0.67
    RegressionTest
    0.66
     Photocase
    0.64
     Wikimedijinoj
    0.62
    Activations Density 0.355%

    No Known Activations