© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6715
    Prev
    Next
    INDEX
    Explanations

    references to faculty members and their roles within an academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.91
    TargetException
    -0.83
     lenker
    -0.81
    FormTagHelper
    -0.79
    RTEE
    -0.78
     colorés
    -0.77
    expandindo
    -0.76
    verwijspagina
    -0.74
     Tirana
    -0.73
     الرياضيه
    -0.73
    POSITIVE LOGITS
     faculty
    2.64
     Faculty
    2.44
    Faculty
    2.42
    faculty
    2.33
     FACULTY
    2.25
     faculties
    1.76
    ULTY
    1.57
     facultad
    1.26
    ulties
    1.22
     Fakult
    1.14
    Activations Density 0.044%

    No Known Activations