© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13995
    Prev
    Next
    INDEX
    Explanations

    criticisms and negative perceptions of people and societal behaviors

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

    Negative opinions and insults

    np_acts-logits-general · gemini-2.0-flash

    people are foolish and obsessed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.46
     kön
    -0.35
     ungewöhn
    -0.34
     méri
    -0.33
    errHandler
    -0.32
    Géographie
    -0.31
    ้อย
    -0.31
     lành
    -0.31
    shtml
    -0.30
     withdrawal
    -0.30
    POSITIVE LOGITS
    UnusedPrivate
    0.78
    SequentialGroup
    0.58
     idiots
    0.52
     fakes
    0.51
     idiot
    0.48
     fad
    0.47
     SqlDbType
    0.47
     fake
    0.46
    cuses
    0.46
     spinners
    0.46
    Activations Density 0.348%

    No Known Activations