© 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. 20-GEMMASCOPE-RES-16K
    11. 3461
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "take" and its variations, indicating a focus on actions and responsibilities

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

    Comes before "advantage," "care," or "precedence"

    np_acts-logits-general · gemini-2.0-flash

    take opportunity or care

    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
    rdı
    -0.56
    Litteratur
    -0.55
    存于互联网档案馆
    -0.54
    IComponent
    -0.51
    nements
    -0.51
    /***/
    -0.50
    seas
    -0.50
    Schemes
    -0.50
    Mediabestanden
    -0.50
    NamedQueries
    -0.49
    POSITIVE LOGITS
     care
    1.31
     advantage
    1.25
     Care
    0.90
    advantage
    0.90
     cared
    0.84
    took
    0.83
     revanche
    0.82
    Care
    0.80
    care
    0.80
    take
    0.80
    Activations Density 0.170%

    No Known Activations