© 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. 22-GEMMASCOPE-RES-16K
    11. 13561
    Prev
    Next
    INDEX
    Explanations

    terms related to contagious infections and direct physical contact

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

    Containing the word "contact"

    np_acts-logits-general · gemini-2.0-flash

    contact

    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
    PhysRevD
    -0.54
    ThroughAttribute
    -0.52
    RunAsync
    -0.52
    VIAF
    -0.51
    SourceChecksum
    -0.51
    PreferredItem
    -0.51
    MemoryWarning
    -0.49
    penup
    -0.49
    Hochspringen
    -0.49
     Tapatalk
    -0.48
    POSITIVE LOGITS
     contact
    3.32
    contact
    2.88
     Contact
    2.79
    Contact
    2.69
     CONTACT
    2.56
     contacto
    2.40
     contacts
    2.38
    CONTACT
    2.37
     kontakt
    2.15
     contato
    2.11
    Activations Density 0.674%

    No Known Activations