© 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. 18-GEMMASCOPE-RES-16K
    11. 11765
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data and its representation

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

    Mathematical or programming notation

    np_acts-logits-general · gemini-2.0-flash

    interaction that, work that, size ==

    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
    8
    -0.80
     eight
    -0.58
     Eight
    -0.57
     VIII
    -0.57
     EIGHT
    -0.54
    ８
    -0.53
    Eight
    -0.52
    gin
    -0.51
    八
    -0.50
    viii
    -0.49
    POSITIVE LOGITS
    ंदीखरीदारी
    0.70
    DataAnnotations
    0.70
     المعيارى
    0.69
     resourceCulture
    0.67
    #+#
    0.65
     SqlCommand
    0.65
    SourceChecksum
    0.63
    Trọng
    0.63
     ujednoznacz
    0.61
    paksa
    0.60
    Activations Density 0.429%

    No Known Activations