© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and reactions to 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
     linkovi
    -0.64
    StructEnd
    -0.59
     चीज़ों
    -0.58
     HttpNotFound
    -0.57
    忑
    -0.56
    fromnode
    -0.56
    PyExc
    -0.53
    MessageTagHelper
    -0.50
     antaranya
    -0.50
     Wikimedijinoj
    -0.49
    POSITIVE LOGITS
     intriguing
    0.75
     intrigued
    0.73
     interest
    0.70
     interesting
    0.69
     intress
    0.61
    interest
    0.58
     interested
    0.57
    Interest
    0.57
    interesting
    0.57
     Interest
    0.56
    Activations Density 0.324%

    No Known Activations