© 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. 999
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to similarity and equality

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

    "... same ... as" construction

    np_acts-logits-general · gemini-2.0-flash

    sameness and similarity comparisons

    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
     дописавши
    -1.15
     kasarigan
    -0.99
     kaarangay
    -0.95
    GraphicsUnit
    -0.93
    yntaxException
    -0.92
    Izvori
    -0.91
    脚注の使い方
    -0.88
    principalTable
    -0.87
    RenderAtEndOf
    -0.86
    homonymie
    -0.84
    POSITIVE LOGITS
     than
    1.29
     as
    1.06
     kuin
    1.03
     THAN
    0.70
     that
    0.64
    than
    0.63
     same
    0.63
    same
    0.62
     wie
    0.58
    Same
    0.55
    Activations Density 0.275%

    No Known Activations