© 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. 31-GEMMASCOPE-RES-16K
    11. 15505
    Prev
    Next
    INDEX
    Explanations

    successful outcomes and achievements in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    actions or verbs describing athletic performance and competition outcomes (scoring, winning, defeating, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.66
    parsedMessage
    -0.66
    Diweddarwch
    -0.64
    Хьажоргаш
    -0.62
    transQ
    -0.61
    featureID
    -0.60
    sizeCache
    -0.57
    internalType
    -0.57
    yntaxException
    -0.56
    INCREF
    -0.55
    POSITIVE LOGITS
     first
    0.74
    初めての
    0.72
     maiden
    0.65
    第一个
    0.59
    初の
    0.57
     its
    0.57
     inaugural
    0.56
    初めて
    0.56
     اولین
    0.55
     erstmals
    0.54
    Activations Density 0.220%

    No Known Activations