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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7247
    Prev
    Next
    INDEX
    Explanations

    transitional phrases that connect ideas in a text

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

    followed by commas

    np_acts-logits-general · gemini-2.0-flash

    connecting words

    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
     that
    -0.59
    /*",
    -0.58
    》、《
    -0.58
     A
    -0.57
    ",@"
    -0.57
     }},
    -0.56
    ;',
    -0.56
    iden
    -0.54
     }}
    -0.54
     }}$,
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.95
    Obrázky
    0.95
    expandindo
    0.92
     resourceCulture
    0.89
     الرياضيه
    0.87
     فريبيس
    0.84
     jScrollPane
    0.82
    WebVitals
    0.80
     дописавши
    0.79
     تانيه
    0.78
    Activations Density 0.466%

    No Known Activations