© 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. 16-GEMMASCOPE-RES-16K
    11. 13403
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific classification and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.96
    featureID
    -0.64
     >=",
    -0.62
    SequentialGroup
    -0.55
    Біографія
    -0.55
     surla
    -0.55
    clusal
    -0.54
     disambiguazione
    -0.53
     Foreword
    -0.53
     Italijanski
    -0.52
    POSITIVE LOGITS
    ("")]
    0.44
     تعدى
    0.39
    yntaxException
    0.32
     ProtoMessage
    0.29
     بسی
    0.28
    Geplaatst
    0.28
     designation
    0.27
    llis
    0.27
    apper
    0.26
    forChild
    0.26
    Activations Density 0.696%

    No Known Activations