© 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. 12-GEMMASCOPE-RES-16K
    11. 10937
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and qualifiers

    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
     chy
    -0.46
     BaseActivity
    -0.43
     cristian
    -0.42
     XXXIII
    -0.42
    cová
    -0.41
    raulic
    -0.41
     pronom
    -0.40
     Chriftian
    -0.40
     tenn
    -0.40
     Christi
    -0.40
    POSITIVE LOGITS
     ब्रेकडाउन
    0.59
    XtraReports
    0.56
     linkovi
    0.55
    ंदीखरीदारी
    0.53
    WithIOException
    0.52
     فريبيس
    0.50
    httphttps
    0.47
     חיצוניים
    0.47
     Italijanski
    0.46
    RTLR
    0.45
    Activations Density 0.315%

    No Known Activations