© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 298
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their manipulation in programming contexts

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

    Strings representing data or objects

    np_acts-logits-general · gemini-2.0-flash

    logging variable values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     архивлан
    -0.93
    Erreferentziak
    -0.78
     createState
    -0.77
     незавершена
    -0.74
     arşivlendi
    -0.73
    AutoScaleMode
    -0.73
    RegistryLite
    -0.71
    cshtml
    -0.71
    endiri
    -0.70
     оригіналу
    -0.69
    POSITIVE LOGITS
    toString
    0.61
    inspect
    0.56
     toString
    0.53
     pprint
    0.53
    ,'\
    0.52
    ToString
    0.52
    ,"\
    0.51
     summary
    0.50
    "></
    0.49
    <eos>
    0.49
    Activations Density 0.074%

    No Known Activations