© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10250
    Prev
    Next
    INDEX
    Explanations

    concepts related to the measurement and expression of time

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

    The neuron looks for mentions or references to time, especially when discussing timing, temporal aspects, timelines, or durations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autorest
    -0.38
     Rosen
    -0.36
    guém
    -0.35
     насељу
    -0.33
    ResponseWriter
    -0.33
    nitzer
    -0.32
     mergeFrom
    -0.32
     оригіналу
    -0.32
    CrossRef
    -0.31
     onCreateView
    -0.31
    POSITIVE LOGITS
     time
    0.89
     timing
    0.86
     timeline
    0.82
     tiempo
    0.81
     Time
    0.80
     시간
    0.79
     χρό
    0.79
     timescale
    0.77
     timed
    0.77
    time
    0.76
    Activations Density 1.082%

    No Known Activations