© 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. 24-GEMMASCOPE-RES-16K
    11. 14712
    Prev
    Next
    INDEX
    Explanations

    mentions of contact or interaction between entities or substances

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

    Contact between objects or people

    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 @ 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
    VIAF
    -0.55
    migrationBuilder
    -0.55
    ltk
    -0.54
    Hochspringen
    -0.52
    RunAsync
    -0.49
    WebElementEntity
    -0.48
    دانشنامهٔ
    -0.47
    ValueGenerated
    -0.46
     устраи
    -0.46
    PreferredItem
    -0.46
    POSITIVE LOGITS
     contact
    2.75
    contact
    2.38
     Contact
    2.29
    Contact
    2.21
     CONTACT
    2.15
     contacts
    2.05
     contacto
    2.04
    CONTACT
    1.99
     contacting
    1.87
     touch
    1.86
    Activations Density 0.572%

    No Known Activations