© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10648
    Prev
    Next
    INDEX
    Explanations

    terms associated with tracking or monitoring

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

    "track" or its variations

    np_acts-logits-general · gemini-2.0-flash

    tracking and following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.49
     OMITBAD
    -0.47
    DotNetBar
    -0.47
     فريبيس
    -0.45
    izers
    -0.45
     Diss
    -0.44
    isier
    -0.43
    MemoryWarning
    -0.42
    Diss
    -0.41
    itarian
    -0.41
    POSITIVE LOGITS
     track
    2.41
     Track
    2.31
    track
    2.23
    Track
    2.22
     TRACK
    2.16
     tracks
    2.06
    TRACK
    2.03
     Tracks
    1.93
     tracked
    1.85
    Tracks
    1.79
    Activations Density 0.096%

    No Known Activations