© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11478
    Prev
    Next
    INDEX
    Explanations

    SQL queries and commands related to data selection and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.48
     betweenstory
    -0.46
    odrome
    -0.45
    WarningLevel
    -0.43
     actionPerformed
    -0.42
     &___
    -0.42
     CanadaChoose
    -0.41
     propOrder
    -0.41
    SequentialGroup
    -0.41
    enderror
    -0.41
    POSITIVE LOGITS
     join
    0.96
    Join
    0.89
     joins
    0.88
     JOIN
    0.88
    join
    0.84
     Join
    0.84
     joining
    0.82
     INNER
    0.79
    JOIN
    0.78
     joined
    0.75
    Activations Density 0.340%

    No Known Activations