© 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. 18-GEMMASCOPE-RES-16K
    11. 9679
    Prev
    Next
    INDEX
    Explanations

    technical terminology and processes related to legal proceedings and decision-making

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

    preceding "when," "after," or "before"

    np_acts-logits-general · gemini-2.0-flash

    temporal sequencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.70
    ANTO
    -0.50
    UnitTesting
    -0.49
    TestBase
    -0.49
    anto
    -0.47
    #
    -0.46
    ული
    -0.45
    ThroughAttribute
    -0.45
     jScrollPane
    -0.44
    tså
    -0.44
    POSITIVE LOGITS
     when
    2.48
    when
    1.91
     cuando
    1.77
     quando
    1.69
     lorsque
    1.68
     ketika
    1.65
     during
    1.60
     khi
    1.58
     WHEN
    1.53
     lorsqu
    1.52
    Activations Density 1.276%

    No Known Activations