© 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. 8722
    Prev
    Next
    INDEX
    Explanations

    numerical values and patterns related to data or measurements

    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
     للمعارف
    -0.68
    窪
    -0.56
     Downey
    -0.56
     lut
    -0.55
    downloader
    -0.54
     Trou
    -0.54
     stu
    -0.53
    PullParser
    -0.53
     downloader
    -0.52
     Dowling
    -0.52
    POSITIVE LOGITS
    6
    1.52
    ۶
    0.85
    ৬
    0.82
    6
    0.82
     ۶
    0.69
     sechs
    0.69
     sixth
    0.68
    7
    0.66
     Sixth
    0.66
     six
    0.65
    Activations Density 0.822%

    No Known Activations