© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    references to decisions or changes in policies and their implications

    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
     esposo
    -0.77
    AVOR
    -0.76
     farther
    -0.74
     flavorful
    -0.73
     favorably
    -0.72
    Someday
    -0.69
     fato
    -0.69
    gotten
    -0.69
     varandra
    -0.68
     gotten
    -0.68
    POSITIVE LOGITS
    Whilst
    1.60
     Whilst
    1.54
     whilst
    1.40
    Firstly
    1.07
    initialise
    1.05
     Firstly
    0.98
     envisage
    0.94
     envisaged
    0.93
     specialises
    0.89
     realises
    0.88
    Activations Density 0.357%

    No Known Activations