© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1259
    Prev
    Next
    INDEX
    Explanations

    the phrase "we would like to" and variations involving requests or invitations

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

    Comes before "like" and indicates a request

    np_acts-logits-general · gemini-2.0-flash

    would like to

    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
     wouldn
    -0.51
     Couldn
    -0.49
    ̍
    -0.47
     Shi
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    wouldn
    -0.44
     دم
    -0.44
    恒
    -0.43
    Couldn
    -0.43
     Wouldn
    -0.43
    POSITIVE LOGITS
     like
    0.83
    tagHelperRunner
    0.77
    脚注の使い方
    0.70
    Cyfarwyddwr
    0.69
     مرئيه
    0.68
    出版年
    0.67
    Referencer
    0.67
     الرياضيه
    0.66
    الدراسه
    0.65
    ImageContext
    0.63
    Activations Density 0.115%

    No Known Activations