© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12880
    Prev
    Next
    INDEX
    Explanations

    statements expressing critiques or observations regarding societal issues or controversies

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

    preceding negative sentiment

    np_acts-logits-general · gemini-2.0-flash

    criticism and negative views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.55
    "])){
    -0.53
    XmlEnum
    -0.53
    mergeFrom
    -0.52
    EnableWeb
    -0.52
    дивиду
    -0.51
     nakalista
    -0.51
     Référence
    -0.50
    oció
    -0.49
     متعلقه
    -0.47
    POSITIVE LOGITS
     critics
    1.93
     Critics
    1.62
     criticism
    1.61
    Critics
    1.55
     criticisms
    1.50
     detra
    1.47
     haters
    1.46
     skep
    1.34
     Criticism
    1.27
     critic
    1.25
    Activations Density 0.517%

    No Known Activations