© 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. 18-GEMMASCOPE-RES-16K
    11. 11400
    Prev
    Next
    INDEX
    Explanations

    discussions around perspectives on race and societal issues

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

    Viewed in a favorable or unfavorable light

    np_acts-logits-general · gemini-2.0-flash

    light most favorable

    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
    Personendaten
    -0.60
    出版年
    -0.55
     del
    -0.52
     Te
    -0.50
    вір
    -0.46
     Del
    -0.46
     кӀош
    -0.46
     La
    -0.46
    itats
    -0.46
    antur
    -0.45
    POSITIVE LOGITS
     favourably
    0.85
     favorably
    0.82
     romanti
    0.66
     light
    0.66
     sounding
    0.63
    XmlAccessType
    0.63
     unfavourable
    0.61
     lustre
    0.61
     glows
    0.60
    light
    0.60
    Activations Density 0.178%

    No Known Activations