© 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. 235
    Prev
    Next
    INDEX
    Explanations

    references to specific local places and organizations

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

    Names of newspapers or publications

    np_acts-logits-general · gemini-2.0-flash

    newspaper and publication titles

    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
     mergeFrom
    -0.63
    Aholisi
    -0.62
    bootstrapcdn
    -0.60
     continúas
    -0.59
    ầy
    -0.57
     newBuilder
    -0.55
     MwSt
    -0.55
     bParam
    -0.54
     exceptionnelle
    -0.54
     Superhost
    -0.52
    POSITIVE LOGITS
     Daily
    1.29
    Daily
    1.18
     News
    1.16
     Times
    1.09
    daily
    1.08
    News
    1.01
     Journal
    1.01
     Herald
    1.00
     news
    0.98
     Gazette
    0.98
    Activations Density 0.247%

    No Known Activations