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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4560
    Prev
    Next
    INDEX
    Explanations

    assertions of correctness or incorrectness in judgments and evaluations

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

    "[word] when" or states of correctness

    np_acts-logits-general · gemini-2.0-flash

    correctness when followed by when

    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
    TintMode
    -0.63
    ArrowToggle
    -0.60
    AsUp
    -0.59
     transfieras
    -0.58
    WithIOException
    -0.57
     pinulongan
    -0.56
    etter
    -0.54
    RegistryLite
    -0.53
    parsedMessage
    -0.53
    ItemBackground
    -0.52
    POSITIVE LOGITS
     when
    1.29
    when
    1.10
     quando
    1.03
     когда
    0.91
    When
    0.91
     cuando
    0.86
     When
    0.86
     WHEN
    0.85
     lorsqu
    0.85
     når
    0.83
    Activations Density 0.307%

    No Known Activations