© 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. 16-GEMMASCOPE-RES-16K
    11. 14592
    Prev
    Next
    INDEX
    Explanations

    structured data and references in scientific literature

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

    Numbers after periods or hyphens

    np_acts-logits-general · gemini-2.0-flash

    Guillou Klinsmann

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.70
    GEBURTSDATUM
    -0.64
    AutoField
    -0.57
     nonatomic
    -0.56
    pruch
    -0.54
    invokeLater
    -0.54
    didSet
    -0.52
    XCTAssertEqual
    -0.52
     ویکی‌پدیا
    -0.50
    coro
    -0.50
    POSITIVE LOGITS
    Билгалдахарш
    0.64
     celta
    0.59
     censura
    0.57
     étranger
    0.55
     suivants
    0.54
     surla
    0.53
     quæ
    0.53
     énergétique
    0.52
    }],
    0.52
    ształ
    0.50
    Activations Density 0.535%

    No Known Activations