© 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 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. 16360
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating future actions or possibilities

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

    preceding "be" or its variants

    np_acts-logits-general · gemini-2.0-flash

    will be, will have been

    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
    ]--;
    -0.68
     has
    -0.64
    ITHUB
    -0.61
     can
    -0.58
    anadium
    -0.56
     had
    -0.56
    featureID
    -0.55
     FormBuilder
    -0.55
     имеет
    -0.55
     memiliki
    -0.55
    POSITIVE LOGITS
    IntoConstraints
    0.86
     be
    0.74
    expandindo
    0.62
    CloseOperation
    0.57
     Waray
    0.55
    AddHtmlAttribute
    0.54
    initWithFrame
    0.53
     být
    0.52
     ensue
    0.50
    InputTagHelper
    0.49
    Activations Density 0.058%

    No Known Activations