© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    the presence of leading indicators or markers in various contexts

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

    Code or questions followed by colons

    np_acts-logits-general · gemini-2.0-flash

    programming template tags

    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
    xdr
    -0.61
    ypeł
    -0.57
    colourful
    -0.56
    AsUp
    -0.55
     maux
    -0.52
    niosek
    -0.51
     Zweiten
    -0.50
    Javadoc
    -0.50
     suaves
    -0.49
    SceneManagement
    -0.49
    POSITIVE LOGITS
     Smarty
    0.93
    Smarty
    0.89
    smarty
    0.80
    ViewFeatures
    0.65
    RegistryLite
    0.63
     verso
    0.60
    tpl
    0.56
    템
    0.56
    ")));
    0.55
     Kolle
    0.55
    Activations Density 0.037%

    No Known Activations