© 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. 4-GEMMASCOPE-RES-16K
    11. 226
    Prev
    Next
    INDEX
    Explanations

    expressions of caution or carefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Croix
    -0.65
     jdbcTemplate
    -0.63
     addSubview
    -0.63
    gamesh
    -0.63
    setImageResource
    -0.62
    AddTagHelper
    -0.62
     Lein
    -0.62
     springfox
    -0.61
     Wynne
    -0.60
    writerow
    -0.59
    POSITIVE LOGITS
     careful
    2.14
     carefully
    2.11
     Careful
    1.98
    Careful
    1.89
     Carefully
    1.87
    caref
    1.83
     soigneusement
    1.72
     cuidadosamente
    1.67
     cuidado
    1.49
     cuidad
    1.47
    Activations Density 0.074%

    No Known Activations