© 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. 22-GEMMASCOPE-RES-16K
    11. 13580
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and gratitude towards clients

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

    Expressing gratitude or appreciation

    np_acts-logits-general · gemini-2.0-flash

    dealing with trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.72
     EconPapers
    -0.68
     DbSet
    -0.62
    ządu
    -0.61
     BeautifulSoup
    -0.58
    Predicted
    -0.58
     Prediction
    -0.57
    iennes
    -0.56
    AsUp
    -0.56
    MethodManager
    -0.55
    POSITIVE LOGITS
     entrust
    1.15
     trusting
    0.98
     trust
    0.95
     trusts
    0.91
     entrusted
    0.82
    trust
    0.81
    TRUST
    0.80
    Trust
    0.79
     Trust
    0.72
     dealing
    0.71
    Activations Density 0.176%

    No Known Activations