© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3266
    Prev
    Next
    INDEX
    Explanations

    concepts related to assembling pieces or components into a complete whole

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Assembling components

    np_acts-logits-general · gemini-2.0-flash

    assembly and fitting parts

    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
    Negative Logits
    뀔
    -0.48
     Swann
    -0.46
     moderated
    -0.45
    뀜
    -0.45
    Scar
    -0.44
    TagHelper
    -0.44
     microfilm
    -0.43
    staan
    -0.43
     Ind
    -0.42
    ceded
    -0.42
    POSITIVE LOGITS
     pieces
    1.50
     puzzle
    1.44
     assembling
    1.43
     jigsaw
    1.41
     piec
    1.39
     assemble
    1.37
    pieces
    1.32
     Pieces
    1.32
     assembled
    1.30
     assemb
    1.29
    Activations Density 0.390%

    No Known Activations