© 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. 15789
    Prev
    Next
    INDEX
    Explanations

    words indicating variety or distinction in a context

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

    Follows "different" and precedes a noun

    np_acts-logits-general · gemini-2.0-flash

    different kinds and types

    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
     vectorielle
    -0.69
     scattata
    -0.68
    UpInside
    -0.68
     umana
    -0.65
    voerd
    -0.64
     lisäksi
    -0.64
     dessutom
    -0.64
     الحره
    -0.64
    śmie
    -0.64
     genomen
    -0.63
    POSITIVE LOGITS
     kinds
    1.03
     kind
    0.86
     types
    0.78
     sorts
    0.77
     than
    0.76
    kinds
    0.70
    liferay
    0.69
     sort
    0.69
    NameInMap
    0.66
     ways
    0.65
    Activations Density 0.097%

    No Known Activations