© 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. 9189
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements related to biological and physical properties

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

    Numbers related to powers of ten

    np_acts-logits-general · gemini-2.0-flash

    large numbers and currency

    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
     half
    -0.69
     double
    -0.66
     halve
    -0.66
     doubles
    -0.64
    half
    -0.62
    doubles
    -0.61
     verdo
    -0.61
     Half
    -0.60
    +#+
    -0.60
    double
    -0.59
    POSITIVE LOGITS
     hundreds
    0.79
     thousands
    0.77
     Hundreds
    0.76
     Thousands
    0.72
     cientos
    0.70
     Савезне
    0.69
     tens
    0.69
     centaines
    0.68
     dizaines
    0.67
    Hundreds
    0.67
    Activations Density 0.628%

    No Known Activations