© 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. 16-GEMMASCOPE-RES-16K
    11. 2786
    Prev
    Next
    INDEX
    Explanations

    references to specific moments and significant occurrences in time

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

    preceding "when," "where," or similar adverbs

    np_acts-logits-general · gemini-2.0-flash

    temporal clauses specifying where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.57
    oredCriteria
    -0.57
    ThroughAttribute
    -0.54
     EconPapers
    -0.54
    PreferredItem
    -0.53
    oa̍t
    -0.53
    :✨
    -0.52
     فريبيس
    -0.52
     समीक्षाएं
    -0.52
     invokingState
    -0.50
    POSITIVE LOGITS
     where
    0.86
    where
    0.69
     où
    0.69
     wherein
    0.67
     times
    0.61
     waarop
    0.59
     hvor
    0.59
    AutoScaleMode
    0.58
    TagMode
    0.57
     donde
    0.57
    Activations Density 0.432%

    No Known Activations