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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6245
    Prev
    Next
    INDEX
    Explanations

    instances of the word "send" or its variations in varying contexts related to communication

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

    verbs of communication or transmission like "send".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giuri
    -0.59
    queryInterface
    -0.57
     whiteColor
    -0.50
    dataIndex
    -0.50
    ValueStyle
    -0.50
    pylab
    -0.49
    SharedCtor
    -0.49
     roleId
    -0.48
     ProgressDialog
    -0.46
     clearColor
    -0.46
    POSITIVE LOGITS
     send
    1.43
    send
    1.31
     Send
    1.28
    Send
    1.27
     sends
    1.20
     sending
    1.15
    SEND
    1.15
     sent
    1.15
     SEND
    1.11
     Sends
    1.10
    Activations Density 0.092%

    No Known Activations