© 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. 22-GEMMASCOPE-RES-16K
    11. 9567
    Prev
    Next
    INDEX
    Explanations

    instances of the word "track" or variations of it in different contexts

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

    "track" or "tracks"

    np_acts-logits-general · gemini-2.0-flash

    track

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricus
    -0.65
     Schult
    -0.63
    atguigu
    -0.63
    zard
    -0.60
    ecma
    -0.57
    glut
    -0.57
     Sond
    -0.55
    enso
    -0.54
    pakking
    -0.54
    deh
    -0.54
    POSITIVE LOGITS
     tracks
    1.11
     Tracks
    1.08
     Track
    1.05
     track
    1.03
    tracks
    1.01
    track
    0.99
     TRACK
    0.94
    Track
    0.92
    TRACK
    0.90
    Tracks
    0.87
    Activations Density 0.052%

    No Known Activations