© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5958
    Prev
    Next
    INDEX
    Explanations

    words related to working or labor

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

    Tokens related to "work" or "working"

    np_acts-logits-general · gemini-2.0-flash

    work with or on

    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
    :✨
    -0.53
    initComponents
    -0.52
    lotl
    -0.51
    LookAnd
    -0.49
    bootstrapcdn
    -0.49
    <!--[
    -0.49
     RFI
    -0.48
    unfinished
    -0.47
    -¿
    -0.47
    cima
    -0.47
    POSITIVE LOGITS
     hard
    0.84
     closely
    0.69
     harder
    0.66
     saites
    0.65
     tirelessly
    0.64
     toward
    0.63
     المعيارى
    0.63
     worked
    0.61
     WORKING
    0.61
     towards
    0.61
    Activations Density 0.089%

    No Known Activations