© 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. 11-GEMMASCOPE-RES-16K
    11. 8122
    Prev
    Next
    INDEX
    Explanations

    header tags and structured elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -0.46
    Билгалдахарш
    -0.46
     still
    -0.45
    ade
    -0.43
    iamo
    -0.41
     cho
    -0.40
    it
    -0.40
    Po
    -0.40
    olla
    -0.40
    sta
    -0.39
    POSITIVE LOGITS
    :✨
    0.79
     CanadaChoose
    0.77
    ſelves
    0.72
     ब्रेकडाउन
    0.69
    новништво
    0.64
     الحره
    0.64
     OFDb
    0.63
    ſelf
    0.63
    transQ
    0.62
     ModelExpression
    0.61
    Activations Density 0.108%

    No Known Activations