© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to product features and qualities

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

    Follows "is"

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjectives and states

    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
    tvguidetime
    -0.68
    ここの
    -0.51
    incoming
    -0.49
    marle
    -0.48
    coarse
    -0.47
     seien
    -0.47
    ത്ത
    -0.47
    tető
    -0.47
    changed
    -0.47
     tertentu
    -0.47
    POSITIVE LOGITS
     pinulongan
    0.80
     fully
    0.63
     currently
    0.62
     defaultstate
    0.61
     lightweight
    0.61
    ArgsConstructor
    0.60
     versatile
    0.60
    يميديا
    0.59
     Cliquez
    0.58
     springfox
    0.57
    Activations Density 0.212%

    No Known Activations