© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    Java-related code syntax and constructs in a programming context

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

    following "at" or ending in "com/org/edu"

    np_acts-logits-general · gemini-2.0-flash

    domain names and package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlSchema
    -0.45
    sequelize
    -0.43
     vě
    -0.42
     Geschle
    -0.41
    くい
    -0.41
     Toro
    -0.39
    tehen
    -0.39
    Swatch
    -0.39
     Vieux
    -0.38
    Toro
    -0.38
    POSITIVE LOGITS
     com
    1.28
    com
    1.27
    org
    1.18
     org
    1.12
    edu
    0.79
     autorytatywna
    0.79
    javax
    0.74
    Com
    0.72
     Org
    0.71
     edu
    0.71
    Activations Density 0.356%

    No Known Activations