© 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 EvalsExportsinterp-engineNEWAPI 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. 1270
    Prev
    Next
    INDEX
    Explanations

    terms related to randomization and selection in experimental contexts

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

    "one of" or "either"

    np_acts-logits-general · gemini-2.0-flash

    one of / either

    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
     insuffisamment
    -0.48
    Viitteet
    -0.47
     tudo
    -0.45
    enumi
    -0.45
     autorytatywna
    -0.44
    Portály
    -0.44
    zog
    -0.43
     հղումներ
    -0.41
    */].
    -0.41
    いけない
    -0.41
    POSITIVE LOGITS
     either
    2.46
    either
    2.24
    Either
    2.11
     Either
    2.05
     alguno
    1.88
     cualquiera
    1.82
     entweder
    1.79
     enten
    1.49
    ITHER
    1.48
     whichever
    1.43
    Activations Density 0.711%

    No Known Activations