© 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. 28-GEMMASCOPE-RES-16K
    11. 7930
    Prev
    Next
    INDEX
    Explanations

    strong expressions of hostility and derogatory language

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

    Negative sentiment/insults

    np_acts-logits-general · gemini-2.0-flash

    slurs and insults

    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
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.64
    énario
    -0.49
    AsUp
    -0.49
    OGND
    -0.48
     kasarigan
    -0.46
    WebElementEntity
    -0.45
    PRNewswire
    -0.45
    ArrowToggle
    -0.44
    Rüyada
    -0.44
    inander
    -0.42
    POSITIVE LOGITS
     stupid
    0.96
    stupid
    0.88
     idiots
    0.79
     scum
    0.76
     idiot
    0.76
    Stupid
    0.75
     Stupid
    0.74
    idiot
    0.73
     bastard
    0.73
     filthy
    0.71
    Activations Density 0.457%

    No Known Activations