© 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. 20-GEMMASCOPE-RES-16K
    6. 8114
    Prev
    Next
    INDEX
    Explanations

    names and terms related to prominent figures and concepts in religion and politics

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

    preceding "in" or suffixes "es," "ses," "ness"

    np_acts-logits-general · gemini-2.0-flash

    Jesus Rashford Goddess Gauss Campus

    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
    NOPQRST
    -0.73
    atrician
    -0.72
    ///</
    -0.70
    iencing
    -0.69
    ябре
    -0.65
    toire
    -0.64
     telefónica
    -0.63
    bleau
    -0.62
    nships
    -0.62
    the
    -0.61
    POSITIVE LOGITS
    es
    1.25
    ses
    1.13
    ES
    1.01
    sing
    0.89
    NESS
    0.78
    ness
    0.77
    sed
    0.75
    nes
    0.70
    ès
    0.68
    hes
    0.65
    Activations Density 0.732%

    No Known Activations