© 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. 16-GEMMASCOPE-RES-16K
    11. 8456
    Prev
    Next
    INDEX
    Explanations

    expressions of extreme preferences or choices regarding life and death, particularly related to familial relationships

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

    Expressing preferences with "rather" or "prefer"

    np_acts-logits-general · gemini-2.0-flash

    rather than / prefer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lapsingToolbar
    -0.74
    protoc
    -0.67
     normalement
    -0.56
    SizeF
    -0.53
     especiais
    -0.50
    greif
    -0.49
     старости
    -0.48
     Khusus
    -0.46
     nødven
    -0.45
     själ
    -0.43
    POSITIVE LOGITS
     than
    1.34
     instead
    1.16
     rather
    1.15
    rather
    1.06
    instead
    1.03
     Rather
    1.01
    Rather
    1.01
     daripada
    1.00
     Instead
    0.97
    Instead
    0.96
    Activations Density 0.244%

    No Known Activations