© 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. 4-GEMMASCOPE-RES-16K
    11. 1179
    Prev
    Next
    INDEX
    Explanations

    quoted text or strings in various contexts, including function or variable names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gour
    -0.43
     ویکی‌آمباردا
    -0.39
    konomi
    -0.39
    จุ
    -0.39
     reconciled
    -0.39
    OfBirth
    -0.39
     pimienta
    -0.39
     للاسماء
    -0.38
    dziel
    -0.38
     acabou
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     pleaſure
    0.70
    omock
    0.70
    AndEndTag
    0.70
    ymce
    0.68
    unknownFields
    0.66
     الرياضيه
    0.65
    ChildScrollView
    0.65
    DOCTYPE
    0.64
     Pingback
    0.64
    Activations Density 0.564%

    No Known Activations