© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8397
    Prev
    Next
    INDEX
    Explanations

    references to brackets and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.68
    Hauptartikel
    -0.66
     transfieras
    -0.64
    ContentAsync
    -0.64
     snippetHide
    -0.63
     "..\..\
    -0.62
    rvats
    -0.61
    IVEREF
    -0.60
    abestanden
    -0.59
     utafitiHapana
    -0.59
    POSITIVE LOGITS
    InjectAttribute
    0.65
     (
    0.63
     onData
    0.61
     rette
    0.56
    InvalidProtocol
    0.54
     ezzel
    0.52
    енча
    0.51
     نسبة
    0.50
    reta
    0.49
     misspelled
    0.49
    Activations Density 0.363%

    No Known Activations