© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5222
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to technical terms

    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
     Meksiku
    -0.64
    ActionEvent
    -0.60
    uple
    -0.59
    POUR
    -0.57
     Bani
    -0.55
    caris
    -0.55
    TypedDataSet
    -0.54
    fromnode
    -0.54
    intios
    -0.54
     opérés
    -0.53
    POSITIVE LOGITS
    bing
    0.60
    usiness
    0.57
    eam
    0.51
    ridge
    0.51
    ecause
    0.50
    lack
    0.50
    ooks
    0.49
    bie
    0.48
    ubble
    0.47
     SIB
    0.47
    Activations Density 0.343%

    No Known Activations