© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 13236
    Prev
    Next
    INDEX
    Explanations

    calls to action or directives related to user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    ImageContext
    -0.61
    Abit
    -0.58
     resourceCulture
    -0.55
    cote
    -0.52
    yntaxException
    -0.52
    ITECH
    -0.51
    NavController
    -0.51
     Hyster
    -0.50
     desti
    -0.49
    Personensuche
    -0.49
    POSITIVE LOGITS
     learn
    1.17
     view
    1.00
     Learn
    0.88
    learn
    0.88
     learns
    0.85
    Learn
    0.78
     View
    0.76
     LEARN
    0.75
     learning
    0.75
     access
    0.74
    Activations Density 0.166%

    No Known Activations