© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10633
    Prev
    Next
    INDEX
    Explanations

    the article "the"

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

    "the" followed by a common word

    np_acts-logits-general · gemini-2.0-flash

    the definite article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ＝
    -0.45
    <eos>
    -0.44
     !(
    -0.43
     contained
    -0.41
     although
    -0.41
     cópia
    -0.40
    切った
    -0.40
     quán
    -0.40
    kini
    -0.40
    dda
    -0.40
    POSITIVE LOGITS
    IUrlHelper
    1.22
     дописавши
    1.14
     resourceCulture
    1.10
     виправивши
    0.96
    TagMode
    0.95
     Мексичка
    0.94
    
    0.93
     للاسماء
    0.86
     surla
    0.86
    ViewFeatures
    0.85
    Activations Density 0.452%

    No Known Activations