© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 3053
    Prev
    Next
    INDEX
    Explanations

    the presence of zero values in a sequence

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

    Loop counters (`i = 0`)

    np_acts-logits-general · gemini-2.0-flash

    loop counters and end markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.68
     Italijanski
    -0.67
     betweenstory
    -0.64
     المعيارى
    -0.61
     otomatig
    -0.60
    ########.
    -0.60
     nahilalakip
    -0.59
     мәкал
    -0.59
    /*
    -0.58
     ujednoznacz
    -0.58
    POSITIVE LOGITS
     hasta
    0.50
     hanggang
    0.48
     onwards
    0.48
     hingga
    0.42
     sampai
    0.42
     until
    0.41
     onward
    0.41
     até
    0.41
     până
    0.40
     đến
    0.39
    Activations Density 0.080%

    No Known Activations