© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3297
    Prev
    Next
    INDEX
    Explanations

    terms related to timeframes and durations associated with processes or events

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

    Tokens related to time duration

    np_acts-logits-general · gemini-2.0-flash

    duration and period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.53
     فريبيس
    -0.51
    DispatchToProps
    -0.51
    期刊论文
    -0.48
    DllImport
    -0.47
    ftagPool
    -0.47
     ब्रेकडाउन
    -0.47
    ')")
    -0.46
    Odkazy
    -0.46
     uska
    -0.45
    POSITIVE LOGITS
     duration
    1.49
     Duration
    1.18
     period
    1.13
    duration
    1.10
     durations
    1.07
     durée
    1.04
    Duration
    1.03
    期间
    0.99
     Period
    0.95
    期間
    0.95
    Activations Density 0.289%

    No Known Activations