© 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. 21-GEMMASCOPE-RES-16K
    11. 5324
    Prev
    Next
    INDEX
    Explanations

    references to time and timing, particularly in terms of years and occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.75
    oredCriteria
    -0.75
     TextInputType
    -0.69
    AccessorTable
    -0.67
    ContentAsync
    -0.64
    ///</
    -0.63
     ModelExpression
    -0.63
     BoxFit
    -0.63
     cdti
    -0.62
    Cyfeiriadau
    -0.60
    POSITIVE LOGITS
     around
    2.90
     round
    2.69
    around
    2.47
     Around
    2.42
    round
    2.42
    Around
    2.35
     AROUND
    2.26
     Round
    2.06
    AROUND
    2.05
    Round
    2.03
    Activations Density 0.205%

    No Known Activations