© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    contradictory or contrasting conjunctions

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

    Sentences containing "but"

    np_acts-logits-general · gemini-2.0-flash

    but contrasting or qualifying

    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
     entera
    -0.39
     entier
    -0.39
     renou
    -0.38
     Gier
    -0.36
     entière
    -0.36
     Schilling
    -0.36
    leges
    -0.36
    FullName
    -0.36
     Internasional
    -0.36
    grés
    -0.35
    POSITIVE LOGITS
    But
    0.85
    WebServlet
    0.84
     But
    0.83
    StoryboardSegue
    0.81
     nakalista
    0.80
    but
    0.78
     BUT
    0.68
    terscotch
    0.68
     AssemblyVersion
    0.68
     but
    0.68
    Activations Density 0.187%

    No Known Activations