© 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. 3-GEMMASCOPE-RES-16K
    11. 9326
    Prev
    Next
    INDEX
    Explanations

    markers of structured data and special formatting in code or markup language

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.78
     plufieurs
    -0.76
    Jeografia
    -0.73
    utnik
    -0.73
     feroit
    -0.71
    __(/*!
    -0.71
    oa̍t
    -0.71
     ainfi
    -0.70
    GEBURTSDATUM
    -0.70
    তথ্যসূত্র
    -0.69
    POSITIVE LOGITS
     didn
    0.67
    __":
    0.62
    '
    0.62
    зопас
    0.60
    setcounter
    0.59
    ’
    0.59
    <eos>
    0.57
     wasn
    0.55
    __':
    0.54
     don
    0.54
    Activations Density 0.278%

    No Known Activations