© 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. 16-GEMMASCOPE-RES-16K
    11. 2781
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was" in various contexts

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

    Comes after "was" or "been"

    np_acts-logits-general · gemini-2.0-flash

    was + verb-ing or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >>>>>>>
    -0.58
    Архівовано
    -0.58
    LLocation
    -0.56
    makeConstraints
    -0.53
    LayoutConstraint
    -0.52
    aarrggbb
    -0.51
     محفوظة
    -0.49
     personalidades
    -0.49
     vált
    -0.49
    حياته
    -0.48
    POSITIVE LOGITS
    XtraGrid
    0.70
     there
    0.58
    లాలు
    0.58
     pyl
    0.56
    zien
    0.55
     Ska
    0.55
     talking
    0.54
     busy
    0.53
    ItemLayout
    0.52
     rocks
    0.52
    Activations Density 0.133%

    No Known Activations