© 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. 16-GEMMASCOPE-RES-16K
    11. 14335
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to scientific and technical subjects

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

    Follows a partial or misspelled word

    np_acts-logits-general · gemini-2.0-flash

    prefix, invocation, muniments, sentencer

    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
    -
    -0.56
    homonymie
    -0.47
    xmlhttp
    -0.47
    -$
    -0.46
     You
    -0.46
    WithIOException
    -0.45
    ())))
    -0.44
    ệm
    -0.42
    -.
    -0.42
     WQS
    -0.41
    POSITIVE LOGITS
    __*/
    0.87
     LoggerFactory
    0.78
    migrationBuilder
    0.77
    adaptiveStyles
    0.75
    ValueStyle
    0.72
    存于互联网档案馆
    0.71
    IntoConstraints
    0.70
     leaſt
    0.69
     Réponses
    0.68
     noqa
    0.64
    Activations Density 1.339%

    No Known Activations