© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 5352
    Prev
    Next
    INDEX
    Explanations

    programming or technical terms related to error handling and data processing

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

    Decoding, parsing, or interpreting data

    np_acts-logits-general · gemini-2.0-flash

    decoding and parsing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     export
    -0.56
     Export
    -0.56
     EXPORT
    -0.55
     oprot
    -0.54
    Export
    -0.52
     send
    -0.51
     exportación
    -0.50
    sendData
    -0.50
    ToSend
    -0.50
    了出去
    -0.49
    POSITIVE LOGITS
     interpreting
    0.92
     decoding
    0.88
     interpret
    0.80
     parsing
    0.80
     interpretation
    0.79
     decoded
    0.78
     decode
    0.77
     Interpreting
    0.76
     unpacking
    0.76
     reception
    0.76
    Activations Density 0.784%

    No Known Activations