© 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. 3973
    Prev
    Next
    INDEX
    Explanations

    CSS styling properties and related elements

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

    Code or style syntax

    np_acts-logits-general · gemini-2.0-flash

    width, serve, print

    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
     considerably
    -0.53
    TabIndex
    -0.51
    Externé
    -0.48
     appreciably
    -0.48
    ConfigureAwait
    -0.45
     dòng
    -0.45
     alternating
    -0.44
     sóng
    -0.44
     significantly
    -0.44
    umenti
    -0.43
    POSITIVE LOGITS
    :✨
    0.82
    featureID
    0.74
    GEBURTSDATUM
    0.70
    ConstraintMaker
    0.67
    contentLoaded
    0.65
     Roskov
    0.65
     protoimpl
    0.63
    ⓧ
    0.62
     تانيه
    0.62
    ///</
    0.62
    Activations Density 0.070%

    No Known Activations