© 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. 2-GEMMASCOPE-RES-16K
    11. 8398
    Prev
    Next
    INDEX
    Explanations

    references to decoding processes and related functions in programming or data processing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.59
    ftagPool
    -0.57
    InjectAttribute
    -0.54
    windowFixed
    -0.53
     rodríguez
    -0.50
    AutoField
    -0.50
     DialogResult
    -0.50
    MessageTagHelper
    -0.50
     informée
    -0.49
     yyq
    -0.48
    POSITIVE LOGITS
    decode
    0.92
     decode
    0.86
    Decode
    0.86
     Decode
    0.84
     degradation
    0.84
    decoded
    0.83
     decoded
    0.81
    解码
    0.73
     degrade
    0.73
     decoding
    0.71
    Activations Density 0.508%

    No Known Activations