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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9422
    Prev
    Next
    INDEX
    Explanations

    references to research studies and methodologies

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

    Following "study," "examine," "analyze," or "investigated."

    np_acts-logits-general · gemini-2.0-flash

    study, examine, analyze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.60
    gwin
    -0.56
     padat
    -0.54
     Bioinformatics
    -0.51
     BaseController
    -0.49
     Surgery
    -0.49
    meldet
    -0.47
     sexuales
    -0.47
     nobile
    -0.47
     Feminist
    -0.47
    POSITIVE LOGITS
     how
    1.26
     cómo
    0.89
    contentLoaded
    0.88
     why
    0.83
    how
    0.82
    cómo
    0.80
     bagaimana
    0.78
     trends
    0.77
     aspects
    0.76
     hvordan
    0.73
    Activations Density 0.619%

    No Known Activations