© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 245
    Prev
    Next
    INDEX
    Explanations

    concepts related to rationality and reasoning

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

    assertions related to logical reasoning or justification

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

    rational basis

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     nahilalakip
    -0.92
    :✨
    -0.82
    Datuak
    -0.76
    AndEndTag
    -0.75
     AssemblyCompany
    -0.75
     kasarigan
    -0.74
     eventdata
    -0.73
    TypedDataSet
    -0.71
    帖最后由
    -0.70
     كومونز
    -0.70
    POSITIVE LOGITS
     rational
    0.67
     Reason
    0.66
    reason
    0.65
     reason
    0.65
     Vernunft
    0.65
    Rational
    0.65
     why
    0.64
     Rational
    0.64
     proč
    0.63
     rationally
    0.63
    Activations Density 0.021%

    No Known Activations