© 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. 24-GEMMASCOPE-RES-16K
    11. 10968
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to coding and programming

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

    Polite words in customer service contexts

    np_acts-logits-general · gemini-2.0-flash

    customer service and support requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     것이다
    -0.52
     bullshit
    -0.51
     fucking
    -0.50
    ImageContext
    -0.50
     fuckin
    -0.49
    localctx
    -0.48
     Chwiliwch
    -0.47
     fat
    -0.47
    makeText
    -0.46
     shit
    -0.46
    POSITIVE LOGITS
    Kindly
    0.45
     
    0.41
     Customer
    0.41
     Kindly
    0.40
     unfortunately
    0.39
     apologize
    0.37
     Regards
    0.37
     ответил
    0.37
     please
    0.36
     customer
    0.36
    Activations Density 0.313%

    No Known Activations