© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12035
    Prev
    Next
    INDEX
    Explanations

    words that express negative opinions or judgments about individuals, particularly focusing on their perceived traits or behaviors

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

    Insults and negative sentiment

    np_acts-logits-general · gemini-2.0-flash

    insults and vulgarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    aarrggbb
    -0.53
     zda
    -0.51
     berätt
    -0.49
    GraphicsUnit
    -0.47
    mişti
    -0.46
     résister
    -0.46
     configureStore
    -0.45
    ジック
    -0.45
    >${
    -0.45
    тербург
    -0.45
    POSITIVE LOGITS
     idiot
    1.14
     idiots
    1.10
     imbec
    1.08
     fools
    1.06
     moron
    1.05
     stupid
    1.03
     morons
    1.03
     dumb
    1.02
     scum
    0.98
     Idiot
    0.98
    Activations Density 0.368%

    No Known Activations