© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7427
    Prev
    Next
    INDEX
    Explanations

    mention of timelines and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cushi
    -0.31
    throwable
    -0.28
     prowadzi
    -0.28
     spare
    -0.28
    spare
    -0.27
    baomidou
    -0.27
    бият
    -0.26
     τέ
    -0.26
    优
    -0.26
     står
    -0.25
    POSITIVE LOGITS
     timeline
    1.70
     timelines
    1.59
     Timeline
    1.55
     chronology
    1.42
    Timeline
    1.41
    timeline
    1.40
     Chronology
    1.38
     Chron
    1.37
    Chron
    1.36
     chron
    1.35
    Activations Density 0.661%

    No Known Activations