© 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. 23-GEMMASCOPE-RES-16K
    11. 9464
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets related to serialization and deserialization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.73
    GEBURTSDATUM
    -0.71
    CppMethod
    -0.68
    ftagPool
    -0.61
    StructEnd
    -0.60
    SaveVideo
    -0.58
     queſta
    -0.57
     Numerade
    -0.56
    Personensuche
    -0.56
    angered
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.43
    SequentialGroup
    0.32
     вот
    0.32
    から
    0.30
    informationen
    0.29
    meyi
    0.28
    IRQn
    0.28
    fromJson
    0.28
    emlrt
    0.28
    serde
    0.27
    Activations Density 0.490%

    No Known Activations