© 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. 18-GEMMASCOPE-RES-16K
    11. 2023
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest expectation or prediction of outcomes

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

    preceding "expected" or its variations

    np_acts-logits-general · gemini-2.0-flash

    as expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.69
     kasarigan
    -0.66
    SourceChecksum
    -0.58
     Numerade
    -0.54
     GenerationType
    -0.52
     linkovi
    -0.52
    StoryboardSegue
    -0.51
    JsonHelper
    -0.51
    
    -0.49
    ⓧ
    -0.48
    POSITIVE LOGITS
     expected
    2.89
    expected
    2.58
     Expected
    2.36
    Expected
    2.29
     EXPECT
    2.04
     expect
    2.04
     Expect
    1.86
     expects
    1.85
     anticipated
    1.82
    EXPECTED
    1.81
    Activations Density 0.487%

    No Known Activations