© 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. 8473
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service policies and procedures

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

    Following periods or order-related words

    np_acts-logits-general · gemini-2.0-flash

    please and similar requests

    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
     <<<<<<<<<<<<<<
    -0.76
    RegressionTest
    -0.68
     AssemblyTitle
    -0.67
     @"/
    -0.67
    providedIn
    -0.66
    Probably
    -0.66
    probably
    -0.64
     probably
    -0.64
    SOUNDBITE
    -0.64
    +][
    -0.63
    POSITIVE LOGITS
     Please
    1.34
    Please
    1.27
     please
    1.24
     PLEASE
    1.04
    please
    1.01
    PLEASE
    0.97
     Bitte
    0.86
     Kindly
    0.85
    Veuillez
    0.84
     veuillez
    0.83
    Activations Density 0.217%

    No Known Activations