© 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. 2198
    Prev
    Next
    INDEX
    Explanations

    references to "track" or "tracking" in various contexts

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

    the word "track" followed by numerical values or identifiers.

    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
     nakalista
    -0.40
    roir
    -0.36
     Consultation
    -0.36
    BeforeAll
    -0.35
    
    -0.35
     Gher
    -0.35
    ang
    -0.35
    complexContent
    -0.34
     hùng
    -0.34
     Consultative
    -0.33
    POSITIVE LOGITS
     Track
    1.00
    Track
    0.91
     track
    0.90
    track
    0.87
    TRACK
    0.81
     TRACK
    0.79
     tracked
    0.78
     tracks
    0.75
     Tracks
    0.72
     trackers
    0.71
    Activations Density 0.066%

    No Known Activations