© 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. 12-GEMMASCOPE-RES-16K
    11. 2546
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to scientific measurements and biological processes

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

    The neuron primarily detects the start-of-sequence / beginning of a document or new text segment.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.74
    DebuggerNonUser
    -0.72
    تقاوى
    -0.71
     мәкал
    -0.62
    StructEnd
    -0.62
    PreInfinity
    -0.60
     незавершена
    -0.59
     disambiguazione
    -0.57
     disponibilités
    -0.56
     FontWeight
    -0.55
    POSITIVE LOGITS
     Definition
    0.53
    RenderAtEndOf
    0.50
     greateſt
    0.49
    AndEndTag
    0.48
     definition
    0.47
     reaſon
    0.47
    DllImport
    0.47
    IntoConstraints
    0.46
     amminist
    0.45
     straff
    0.45
    Activations Density 0.516%

    No Known Activations