© 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. 23-GEMMASCOPE-RES-16K
    11. 2440
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or learning experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.51
     Italijanski
    -0.47
     GetEnumerator
    -0.47
    كويكب
    -0.47
     picioare
    -0.45
     tiegħ
    -0.44
     răsp
    -0.44
     depresión
    -0.43
     tumours
    -0.43
     anaemia
    -0.43
    POSITIVE LOGITS
     about
    0.59
    Diweddarwch
    0.56
     what
    0.56
     information
    0.50
     về
    0.49
     Information
    0.47
     EconPapers
    0.45
    เกี่ยวกับ
    0.45
     nothing
    0.44
     What
    0.44
    Activations Density 0.295%

    No Known Activations