© 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. 15459
    Prev
    Next
    INDEX
    Explanations

    Java annotations used in Spring framework configurations and entity definitions

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

    Java annotations (@Bean, @Entity, etc.)

    np_acts-logits-general · gemini-2.0-flash

    Java annotations and programming constructs

    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
    ).__
    -0.86
     Савезне
    -0.86
     للمعارف
    -0.85
     незавершена
    -0.83
    typeparam
    -0.79
    interopRequire
    -0.76
     surla
    -0.75
    بوابة
    -0.74
    principalColumn
    -0.73
     QtCore
    -0.71
    POSITIVE LOGITS
    ↵
    0.99
    (
    0.80
    ()
    0.64
     (
    0.58
    .
    0.45
    ("
    0.44
     //
    0.44
     meerdere
    0.43
    //(
    0.43
    )
    0.42
    Activations Density 0.019%

    No Known Activations