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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14713
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and staying connected

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

    "get in touch" or contact information

    np_acts-logits-general · gemini-2.0-flash

    get in touch

    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
    saraba
    -0.71
    LookAnd
    -0.70
    webElementXpaths
    -0.69
    OGND
    -0.67
     propOrder
    -0.66
    انيف
    -0.64
    المناصب
    -0.64
     Anſ
    -0.63
    djangoproject
    -0.61
    afficheront
    -0.61
    POSITIVE LOGITS
     contact
    2.75
    contact
    2.36
     Contact
    2.26
    Contact
    2.22
     CONTACT
    2.00
     contacto
    1.97
     touch
    1.90
     contacts
    1.82
     contacting
    1.82
    CONTACT
    1.79
    Activations Density 0.151%

    No Known Activations