© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 9546
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly in terms of clocks and specific time indicators

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

    clock time expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wią
    -0.40
     sementes
    -0.38
     giras
    -0.38
     diseños
    -0.38
     INTERESAR
    -0.37
     vété
    -0.37
     Erwä
    -0.35
     vœ
    -0.35
     zmar
    -0.34
     gymnast
    -0.33
    POSITIVE LOGITS
    clock
    1.32
    Clock
    0.90
    CLOCK
    0.84
     clock
    0.83
     CLOCK
    0.82
    AnchorStyles
    0.81
     Clock
    0.81
     clocks
    0.70
     clocked
    0.67
    AndEndTag
    0.65
    Activations Density 0.004%

    No Known Activations