© 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. 30-GEMMASCOPE-RES-16K
    11. 12570
    Prev
    Next
    INDEX
    Explanations

    instances of the word "did."

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

    "I'd" or "would" contractions

    np_acts-logits-general · gemini-2.0-flash

    'd followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -1.00
    not
    -0.75
     Not
    -0.48
     NOT
    -0.47
     tidak
    -0.45
    Not
    -0.44
     nicht
    -0.44
     among
    -0.39
    among
    -0.39
    NOT
    -0.38
    POSITIVE LOGITS
    enumii
    0.57
    iddhar
    0.56
     estekak
    0.56
    ArgsConstructor
    0.55
     typelib
    0.54
     चीज़ों
    0.51
     الحره
    0.51
    нгред
    0.50
    SequentialGroup
    0.50
    Ivoire
    0.49
    Activations Density 0.070%

    No Known Activations