© 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. 11355
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion or reflection

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

    "For me" or "to me" phrases

    np_acts-logits-general · gemini-2.0-flash

    personal perspective

    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
    SourceChecksum
    -0.70
     typelib
    -0.68
    EndGlobalSection
    -0.67
    ArrowToggle
    -0.63
     dolayı
    -0.62
     kepada
    -0.60
    Personendaten
    -0.59
     ویکی‌پدی
    -0.59
     nahilalakip
    -0.58
     voidaan
    -0.57
    POSITIVE LOGITS
     NSCoder
    0.71
    来说
    0.67
    來說
    0.62
     personally
    0.62
    COUVER
    0.61
    而言
    0.59
     persönlich
    0.55
     it
    0.54
    databind
    0.53
    orek
    0.50
    Activations Density 0.093%

    No Known Activations