© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    moments of anticipation or transition in the narrative

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

    phrases indicating a transition or decision point in time, particularly the phrase "it was time to."

    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
    grès
    -0.51
    extAlignment
    -0.45
    balleur
    -0.43
    úblico
    -0.42
     Histórico
    -0.40
     disambiguazione
    -0.39
    idemiology
    -0.37
    CloseOperation
    -0.36
    Pautan
    -0.36
     Roskov
    -0.36
    POSITIVE LOGITS
     time
    2.02
     tijd
    1.38
    time
    1.35
     Time
    1.20
    Time
    1.20
     время
    1.06
     czas
    1.05
     tiempo
    1.02
    时候
    1.02
     TIME
    1.01
    Activations Density 0.232%

    No Known Activations