© 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. 20-GEMMASCOPE-RES-16K
    11. 15212
    Prev
    Next
    INDEX
    Explanations

    assertions made about truth and facts, especially regarding financial implications and social narratives

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

    truth or reality

    np_acts-logits-general · gemini-2.0-flash

    accepting truth or reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PullParser
    -0.69
    ContentAsync
    -0.66
    migrationBuilder
    -0.64
     Италијани
    -0.63
     صوتيه
    -0.63
    thâu
    -0.61
     typelib
    -0.61
    पया
    -0.60
    awaiter
    -0.60
    SharedDtor
    -0.60
    POSITIVE LOGITS
     reality
    2.75
     facts
    2.46
     truth
    2.33
    reality
    2.31
     realities
    2.11
     Reality
    2.11
    facts
    2.05
    Reality
    2.00
     Facts
    1.97
    Fact
    1.95
    Activations Density 0.413%

    No Known Activations