© 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. 16-GEMMASCOPE-RES-16K
    11. 8445
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to contacting or reaching out for communication

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

    "Contact" followed by personal information

    np_acts-logits-general · gemini-2.0-flash

    contact information and us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rigs
    -0.65
    onalds
    -0.64
     Arya
    -0.63
     Yud
    -0.62
     Kers
    -0.60
    Machines
    -0.59
    digm
    -0.59
     Schur
    -0.58
     rigged
    -0.57
     Babylonian
    -0.57
    POSITIVE LOGITS
     contact
    1.46
     contacts
    1.36
     Contact
    1.35
    contact
    1.34
     CONTACT
    1.32
    CONTACT
    1.30
    Contact
    1.27
     Contacts
    1.25
    Contacts
    1.18
     kontak
    1.16
    Activations Density 0.072%

    No Known Activations