© 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. 9439
    Prev
    Next
    INDEX
    Explanations

    references to specific events or situations that imply a sense of hardship or struggle

    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
     nécessairement
    -0.73
     refrigerador
    -0.67
    dized
    -0.66
    ">//
    -0.66
     boletos
    -0.65
     figliu
    -0.62
     duquel
    -0.62
    ɚ
    -0.61
     licorne
    -0.61
    ômico
    -0.60
    POSITIVE LOGITS
     bloke
    0.99
     dodgy
    0.92
     bits
    0.90
     lads
    0.88
     £
    0.88
     posh
    0.83
     cheeky
    0.83
     abit
    0.79
     Sorted
    0.79
     sorted
    0.76
    Activations Density 0.600%

    No Known Activations