© 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. 24-GEMMASCOPE-RES-16K
    11. 4093
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific patent references in the text

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

    The number 9

    np_acts-logits-general · gemini-2.0-flash

    nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſen
    -0.69
    isure
    -0.64
     ſei
    -0.63
     uLocal
    -0.63
     ſont
    -0.62
    iſter
    -0.62
    majánló
    -0.62
     ſur
    -0.61
     isoto
    -0.60
    ſam
    -0.60
    POSITIVE LOGITS
    9
    1.47
     nueve
    0.79
     nine
    0.78
    8
    0.75
    ９
    0.70
     ninety
    0.69
    ۹
    0.68
     neun
    0.67
     Nine
    0.66
     Ninth
    0.64
    Activations Density 0.768%

    No Known Activations