© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12737
    Prev
    Next
    INDEX
    Explanations

    phrases that express comparisons or alternative scenarios

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

    "Or" followed by a contrasting word

    np_acts-logits-general · gemini-2.0-flash

    or rather

    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
    MLLoader
    -0.91
     للاسماء
    -0.86
     تانيه
    -0.83
    AndEndTag
    -0.75
     linkovi
    -0.73
     كومونز
    -0.72
     newBuilder
    -0.72
     raiſ
    -0.70
     createState
    -0.70
    RegressionTest
    -0.70
    POSITIVE LOGITS
    чнее
    0.86
     rather
    0.74
     plutôt
    0.64
     maybe
    0.64
     should
    0.64
    というか
    0.63
     better
    0.60
     sorry
    0.58
     forse
    0.57
    sic
    0.57
    Activations Density 0.180%

    No Known Activations