© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 301
    Prev
    Next
    INDEX
    Explanations

    references to "track" and related terms in various contexts, indicating a focus on tracking systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morley
    -0.74
    المناصب
    -0.73
     écl
    -0.69
     Gerr
    -0.68
     newValue
    -0.68
     Valeria
    -0.67
    ngOnInit
    -0.64
    bfs
    -0.64
     Maier
    -0.64
    Allo
    -0.64
    POSITIVE LOGITS
     track
    2.78
     Track
    2.73
     tracks
    2.68
     TRACK
    2.60
    Track
    2.59
    track
    2.55
     Tracks
    2.50
    TRACK
    2.41
    tracks
    2.35
    Tracks
    2.21
    Activations Density 0.027%

    No Known Activations