© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    terms related to late-night activities or timing

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

    the word "late" when it appears at the beginning of a time-related phrase or temporal expression.

    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
     Stoppers
    -0.40
     تضيفلها
    -0.38
     '\\;'
    -0.38
    Amos
    -0.37
     estekak
    -0.36
     typelib
    -0.36
    endphp
    -0.35
    clerview
    -0.34
    CIL
    -0.34
     ervan
    -0.34
    POSITIVE LOGITS
    Late
    0.70
     Late
    0.67
    comers
    0.66
     LATE
    0.63
     lamented
    0.60
     late
    0.57
    comer
    0.56
     NIGHT
    0.55
     stages
    0.54
     night
    0.53
    Activations Density 0.153%

    No Known Activations