© 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. 3-GEMMASCOPE-RES-16K
    11. 4532
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structure in programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     utafitiHapana
    -0.88
     виправивши
    -0.81
     beginnetje
    -0.73
    TypedDataSet
    -0.69
    AccessorTable
    -0.66
    Демографія
    -0.65
     EconPapers
    -0.64
    __(/*!
    -0.63
    mobileqq
    -0.62
    Datuak
    -0.61
    POSITIVE LOGITS
    prefixer
    0.53
    classnames
    0.49
    fortawesome
    0.48
     pareti
    0.47
     colors
    0.47
    currentColor
    0.46
     automatiques
    0.46
    gdx
    0.45
    TargetApi
    0.44
     AttributeSet
    0.44
    Activations Density 0.580%

    No Known Activations