© 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. 22-GEMMASCOPE-RES-16K
    11. 7401
    Prev
    Next
    INDEX
    Explanations

    the word "well" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Well," followed by various continuations

    np_acts-logits-general · gemini-2.0-flash

    well, done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     religieuses
    -0.54
     jsPsych
    -0.53
    *~*~
    -0.48
    不信
    -0.48
     Lehrer
    -0.48
    venirs
    -0.47
     negativas
    -0.47
    FIF
    -0.47
    Afghan
    -0.46
     تعدى
    -0.46
    POSITIVE LOGITS
     done
    0.79
     Done
    0.76
    springs
    0.73
     behaved
    0.69
    spring
    0.69
     versed
    0.68
    known
    0.67
     deserved
    0.65
     sûr
    0.64
    RSpec
    0.62
    Activations Density 0.064%

    No Known Activations