© 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. 11484
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and connections between different entities or concepts

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

    Follows forms of "to be" ("is", "are", "were")

    np_acts-logits-general · gemini-2.0-flash

    are followed by descriptors

    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
     itself
    -0.83
     its
    -0.81
     espirituales
    -0.76
    SourceChecksum
    -0.76
    Its
    -0.76
    itself
    -0.75
     Its
    -0.75
     kuris
    -0.74
     médicaux
    -0.74
    它的
    -0.73
    POSITIVE LOGITS
     themselves
    1.26
     ones
    1.23
     которые
    1.06
    themselves
    1.04
     those
    1.02
     amelyek
    0.99
     serem
    0.98
     are
    0.96
    those
    0.95
    它们
    0.93
    Activations Density 1.863%

    No Known Activations