© 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. 22-GEMMASCOPE-RES-16K
    11. 3733
    Prev
    Next
    INDEX
    Explanations

    terms related to nanoparticles and their properties

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

    immediately preceding "layer", "robe", or ending in "p"

    np_acts-logits-general · gemini-2.0-flash

    nanopatterning, riboprobe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Instructional
    -0.59
    bootstrapcdn
    -0.57
    neither
    -0.55
     Exceptional
    -0.55
     posesión
    -0.55
     Eocene
    -0.54
     otherwise
    -0.54
     instructional
    -0.53
    Pfalz
    -0.53
    otherwise
    -0.53
    POSITIVE LOGITS
    enumi
    0.56
     EconPapers
    0.55
    ara
    0.52
     GenerationType
    0.52
    arti
    0.51
    twimg
    0.51
    harma
    0.50
    lay
    0.50
    references
    0.49
    ri
    0.48
    Activations Density 0.314%

    No Known Activations