© 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. 25-GEMMASCOPE-RES-16K
    11. 2447
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those that seem to reference people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.68
     trời
    -0.60
    elf
    -0.53
    LookAnd
    -0.52
    libft
    -0.51
     façons
    -0.51
    omock
    -0.50
     Usher
    -0.49
    avons
    -0.48
    ing
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.61
    multer
    0.56
    ADELPHIA
    0.55
    oi
    0.54
     intptr
    0.52
    UnsafeEnabled
    0.50
    antro
    0.49
    utriche
    0.47
    BackStack
    0.47
    berto
    0.47
    Activations Density 0.252%

    No Known Activations