Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2682
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to punctuality and timeliness in customer service contexts

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

    associated with lateness or delays

    np_acts-logits-general · gemini-2.0-flash

    minutes too late

    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
    GenerationType
    -0.59
    esez
    -0.56
    WebServlet
    -0.55
    offsetof
    -0.50
    ufig
    -0.50
    fortawesome
    -0.48
     JAXBElement
    -0.47
    asable
    -0.47
    ivir
    -0.47
    ACHED
    -0.46
    POSITIVE LOGITS
     late
    1.89
     delayed
    1.71
     delay
    1.66
     Late
    1.63
    Late
    1.62
     tard
    1.60
     LATE
    1.58
     delays
    1.55
    late
    1.51
     Delayed
    1.46
    Activations Density 0.171%

    No Known Activations