© 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. 16-GEMMASCOPE-RES-16K
    6. 14165
    Prev
    Next
    INDEX
    Explanations

    information related to live broadcasts and event scheduling

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

    Availability or accessibility

    np_acts-logits-general · gemini-2.0-flash

    media availability

    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
    brengen
    -0.53
     exaggerated
    -0.52
     convincing
    -0.50
     Lettre
    -0.47
     agences
    -0.47
     Innoc
    -0.46
     inoculated
    -0.45
     civile
    -0.45
     assisting
    -0.44
     russe
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.86
    IVEREF
    0.86
     streaming
    0.85
     Streaming
    0.71
    ьаж
    0.70
     المعيارى
    0.68
     '\\;'
    0.67
    ThroughAttribute
    0.67
     defaultstate
    0.67
     مرئيه
    0.67
    Activations Density 0.175%

    No Known Activations