© 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. 15-GEMMASCOPE-RES-16K
    11. 911
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax indicating object references and method invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.56
    +#+#
    -0.44
     ujednoznacz
    -0.43
     cade
    -0.42
    条
    -0.42
    memoized
    -0.40
     оз
    -0.39
     cio
    -0.39
     apt
    -0.39
     BRE
    -0.39
    POSITIVE LOGITS
    __(/*!
    0.71
     resourceCulture
    0.64
     <<<<<<<<<<<<<<
    0.54
     jScrollPane
    0.49
     Процитовано
    0.47
    \{\\
    0.47
    клопе
    0.46
     nahilalakip
    0.46
     Moscú
    0.45
    pulseira
    0.44
    Activations Density 0.474%

    No Known Activations