© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concepts of truth and reality

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

    "reality" or "truth"

    np_acts-logits-general · gemini-2.0-flash

    reality and truth

    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
    gyz
    -0.56
     newBuilder
    -0.55
    AddTagHelper
    -0.55
    addPreferredGap
    -0.53
    yarnpkg
    -0.52
    rogly
    -0.51
     kör
    -0.51
    ագրություններ
    -0.51
    izoen
    -0.50
    logenetic
    -0.50
    POSITIVE LOGITS
     Truths
    0.74
    fulness
    0.68
     truths
    0.67
    Reality
    0.63
     distortion
    0.61
     Reality
    0.61
     realities
    0.60
     Squal
    0.58
     distorted
    0.58
     Xunit
    0.57
    Activations Density 0.115%

    No Known Activations