© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11951
    Prev
    Next
    INDEX
    Explanations

    conclusive statements or summaries in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.47
    
    -0.40
     wireType
    -0.36
     dad
    -0.34
    PLANATION
    -0.33
     disambiguazione
    -0.33
     censo
    -0.33
     factory
    -0.33
     sorella
    -0.33
     exclusively
    -0.33
    POSITIVE LOGITS
     overall
    2.16
     Overall
    2.09
    Overall
    2.08
    overall
    1.95
    总体
    1.50
    OVERALL
    1.43
    整體
    1.41
     Insgesamt
    1.32
     insgesamt
    1.30
     Altogether
    1.27
    Activations Density 0.249%

    No Known Activations