© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8479
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and definitions of "unit."

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

    "unit" or "units"

    np_acts-logits-general · gemini-2.0-flash

    unit of, unit followed by another word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.43
     hề
    -0.41
     tepi
    -0.40
     géographique
    -0.40
     Перейти
    -0.38
    ütfen
    -0.37
     Schoen
    -0.36
     prawo
    -0.36
    ksessa
    -0.36
    diğinde
    -0.35
    POSITIVE LOGITS
     Unit
    0.99
     unit
    0.97
     UNIT
    0.96
     Units
    0.95
    Unit
    0.91
     units
    0.90
    unit
    0.89
    units
    0.83
    Units
    0.83
     AssemblyTitle
    0.81
    Activations Density 0.110%

    No Known Activations