© 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. 14804
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced technology and its implications on humanity

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

    Follows specific words (he, methods, Andre, can, should)

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by verbs

    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
     ارش
    -0.52
    iciens
    -0.52
    })}\
    -0.50
     nakalista
    -0.50
     Kit
    -0.49
    Conduct
    -0.48
    InjectAttribute
    -0.48
     الحره
    -0.47
    lowe
    -0.47
     conducting
    -0.46
    POSITIVE LOGITS
     przecież
    0.60
    mongoose
    0.58
    addCriterion
    0.57
    lafen
    0.56
    WebServlet
    0.55
    iculous
    0.55
     convertView
    0.54
     sorely
    0.54
     embody
    0.54
     dalamnya
    0.53
    Activations Density 0.256%

    No Known Activations