© 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. 24-GEMMASCOPE-RES-16K
    6. 12251
    Prev
    Next
    INDEX
    Explanations

    numerical data and relevant statistics in the text

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

    Numerical values

    np_acts-logits-general · gemini-2.0-flash

    names and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Woodward
    -0.79
     Coleman
    -0.76
     Strickland
    -0.74
     Iri
    -0.72
     Luci
    -0.70
     Nikki
    -0.69
     Glaser
    -0.67
    Coleman
    -0.67
     Jamestown
    -0.67
    elemField
    -0.66
    POSITIVE LOGITS
     Nexus
    0.70
     Kuo
    0.68
     Patricia
    0.64
     Stafford
    0.62
     Jolie
    0.61
     Anja
    0.60
     Leslie
    0.59
     NAC
    0.59
    liau
    0.58
    Patricia
    0.58
    Activations Density 1.017%

    No Known Activations