© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15088
    Prev
    Next
    INDEX
    Explanations

    terms related to upper and lower bounds in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.73
    出版年
    -0.70
     eventId
    -0.68
    igurumi
    -0.66
     ſelbſt
    -0.63
    ofday
    -0.62
     مرئيه
    -0.62
    SequentialGroup
    -0.62
    charCode
    -0.61
     témoig
    -0.60
    POSITIVE LOGITS
     upper
    1.20
     Upper
    1.16
    Upper
    1.08
     lower
    1.07
     Lower
    1.00
    upper
    1.00
     UPPER
    0.98
    Lower
    0.94
     higher
    0.92
     LOWER
    0.90
    Activations Density 0.237%

    No Known Activations