© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13245
    Prev
    Next
    INDEX
    Explanations

    references to celebrity appearances and partnerships

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

    Tokens followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    product launches and announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quelquefois
    -0.79
     ibland
    -0.72
     pitié
    -0.71
     démission
    -0.69
     brukar
    -0.69
     solito
    -0.67
     guère
    -0.65
    SBATCH
    -0.64
     enfans
    -0.63
     bénévoles
    -0.61
    POSITIVE LOGITS
     activations
    0.73
     activation
    0.73
     unveiled
    0.69
     campaign
    0.65
     experiential
    0.65
     launch
    0.63
     launching
    0.63
     featuring
    0.62
     exclusive
    0.62
     unveil
    0.60
    Activations Density 0.143%

    No Known Activations