© 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. 9-GEMMASCOPE-RES-16K
    11. 8541
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.01
    GEBURTSDATUM
    -0.88
     pinulongan
    -0.86
     незавершена
    -0.84
    uxxxx
    -0.83
    ſicht
    -0.78
     Wikimedijinoj
    -0.78
    GTCX
    -0.76
    WebElementEntity
    -0.76
     deſſen
    -0.75
    POSITIVE LOGITS
     explained
    0.31
     told
    0.27
     described
    0.26
     afirma
    0.25
     attended
    0.24
     explicou
    0.24
     afirmó
    0.23
     influ
    0.23
     explicó
    0.23
     stated
    0.23
    Activations Density 0.198%

    No Known Activations