© 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. 16-GEMMASCOPE-RES-16K
    11. 13026
    Prev
    Next
    INDEX
    Explanations

    affirmations or confirmations in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autonome
    -0.37
     cinquième
    -0.36
     Witness
    -0.35
     portefeuille
    -0.35
     isolé
    -0.34
     épais
    -0.34
     Vok
    -0.34
     operations
    -0.34
     Fußballspieler
    -0.34
    WriteLiteral
    -0.34
    POSITIVE LOGITS
    eraard
    0.97
    følgelig
    0.88
    verständlich
    0.88
     natürlich
    0.86
     Natürlich
    0.86
    Natürlich
    0.80
    当然
    0.78
     natuurlijk
    0.76
    czywiście
    0.75
     Naturally
    0.75
    Activations Density 0.053%

    No Known Activations