© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12565
    Prev
    Next
    INDEX
    Explanations

    words associated with work and effort

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

    "Work" followed by an adverb or preposition

    np_acts-logits-general · gemini-2.0-flash

    work plus hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verzorg
    -0.59
     peines
    -0.55
    xase
    -0.54
    håll
    -0.53
     TestBed
    -0.49
     larmes
    -0.49
    ونز
    -0.49
     attentes
    -0.49
     kullanılan
    -0.48
     waard
    -0.48
    POSITIVE LOGITS
     toward
    0.73
     towards
    0.72
     hard
    0.69
     overtime
    0.66
     wonders
    0.65
     backwards
    0.64
    lafen
    0.64
     miracles
    0.63
     daran
    0.62
    CppMethod
    0.62
    Activations Density 0.071%

    No Known Activations