© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6200
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a time reference, particularly those related to "last" or recent events

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

    the word "Last" at the beginning of sentences or phrases.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ơi
    -0.35
     beitragen
    -0.34
     Audiodateien
    -0.31
     autorytatywna
    -0.31
    complexContent
    -0.29
    hie
    -0.29
    tagHelperRunner
    -0.29
    ODD
    -0.29
    toli
    -0.29
     apre
    -0.29
    POSITIVE LOGITS
     getLast
    0.73
     LAST
    0.66
     Last
    0.66
    last
    0.65
     resort
    0.63
    ingly
    0.62
     Dernière
    0.62
    Last
    0.62
    Resort
    0.60
    resort
    0.60
    Activations Density 0.081%

    No Known Activations