© 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. 36-GEMMASCOPE-RES-16K
    6. 15460
    Prev
    Next
    INDEX
    Explanations

    structured data or numerical references within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -1.04
    GEBURTSDATUM
    -0.93
     незавершена
    -0.84
     témoig
    -0.84
    ſchaft
    -0.84
     Administrativna
    -0.84
     Италијани
    -0.80
    ésultats
    -0.79
     queſta
    -0.77
    oredCriteria
    -0.75
    POSITIVE LOGITS
     jongen
    0.35
     trasero
    0.34
     mijne
    0.33
     venganza
    0.33
     stesse
    0.30
     stessi
    0.30
     enfermo
    0.30
     budowy
    0.30
     zijne
    0.29
     vecino
    0.29
    Activations Density 1.714%

    No Known Activations