© 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. 33-GEMMASCOPE-RES-16K
    11. 12091
    Prev
    Next
    INDEX
    Explanations

    key automotive features and technology terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTGC
    -0.50
    Ӕ
    -0.38
    RTCK
    -0.36
    FED
    -0.35
     Lw
    -0.35
     DialogInterface
    -0.34
    -------
    -0.34
    xase
    -0.33
     Wikimédia
    -0.33
    ohjel
    -0.33
    POSITIVE LOGITS
     dashboard
    1.06
     instrument
    1.05
    instrument
    1.00
     instruments
    0.92
     dash
    0.91
     dashboards
    0.89
    instruments
    0.88
    Instrument
    0.88
     Instrument
    0.87
     console
    0.84
    Activations Density 0.226%

    No Known Activations