© 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. 3-GEMMASCOPE-RES-16K
    11. 9732
    Prev
    Next
    INDEX
    Explanations

    expressions of dislike or hatred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementGuid
    -0.84
    zzleHttp
    -0.75
    DoubleQuotes
    -0.71
    lende
    -0.70
     doInBackground
    -0.68
     nahilalakip
    -0.68
     ddelweddau
    -0.67
    URLException
    -0.65
    Viitteet
    -0.65
    Tracce
    -0.65
    POSITIVE LOGITS
     hate
    2.99
     Hate
    2.56
    Hate
    2.50
    hate
    2.47
     hates
    2.40
     HATE
    2.38
     hated
    2.12
     hating
    2.10
     hatred
    2.07
     hateful
    1.76
    Activations Density 0.054%

    No Known Activations