© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 915
    Prev
    Next
    INDEX
    Explanations

    phrases related to returns, customer service, and payment policies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Followed by "please"

    np_acts-logits-general · gemini-2.0-flash

    payment instructions

    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
    Negative Logits
     justement
    -0.54
    supposed
    -0.48
     Hardly
    -0.44
     вроде
    -0.43
     pourtant
    -0.43
     Pourtant
    -0.42
    FirstResponder
    -0.42
    Кстати
    -0.41
     hardly
    -0.40
    vertx
    -0.40
    POSITIVE LOGITS
     please
    0.89
    Please
    0.76
     Please
    0.75
     Италијани
    0.73
     prosím
    0.73
     hereby
    0.69
    PLEASE
    0.69
    please
    0.68
     olacaktır
    0.66
     PLEASE
    0.65
    Activations Density 0.750%

    No Known Activations