© 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. 3808
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expectation, performance, and outcomes

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

    "Live up to" and related forms

    np_acts-logits-general · gemini-2.0-flash

    live up to expectations

    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
    aarrggbb
    -0.68
     متعلقه
    -0.63
    ագրություններ
    -0.61
    ólica
    -0.58
    FormTagHelper
    -0.58
    simpleType
    -0.56
     estekak
    -0.56
    BeginContext
    -0.56
    rrggbb
    -0.54
    بوابة
    -0.54
    POSITIVE LOGITS
     lived
    1.61
     living
    1.51
     live
    1.43
    Living
    1.40
     Living
    1.36
    living
    1.31
     LIVING
    1.31
     lives
    1.29
     Live
    1.22
     Lived
    1.22
    Activations Density 0.200%

    No Known Activations