© 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. 12360
    Prev
    Next
    INDEX
    Explanations

    assertions about possibilities and hypothetical situations

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

    "It would be" or similar conditional phrases

    np_acts-logits-general · gemini-2.0-flash

    evaluative judgment

    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
    出版年
    -0.64
    uxxxx
    -0.64
     poffe
    -0.63
     uſe
    -0.63
     chofe
    -0.63
     uſed
    -0.60
     fubject
    -0.59
     Diſ
    -0.59
     themſelves
    -0.59
     Majefty
    -0.59
    POSITIVE LOGITS
     unfair
    1.11
     wrong
    1.09
     foolish
    1.07
    wrong
    0.93
     unjust
    0.92
     unreasonable
    0.92
     unwise
    0.91
     silly
    0.90
     folly
    0.89
     fair
    0.86
    Activations Density 0.358%

    No Known Activations