© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1111
    Prev
    Next
    INDEX
    Explanations

    characters and special symbols commonly used in programming and data formats

    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
    立て
    -0.41
    ņem
    -0.41
    ,
    -0.39
     geri
    -0.37
    ↵
    -0.37
     qu
    -0.37
     fortuna
    -0.37
     suun
    -0.37
    reiche
    -0.36
     spread
    -0.36
    POSITIVE LOGITS
     виправивши
    1.09
    UnusedPrivate
    1.02
    StructEnd
    0.90
    脚注の使い方
    0.89
     AssemblyCulture
    0.89
     صوتيه
    0.88
     otomatig
    0.84
    ChildScrollView
    0.84
    ValueStyle
    0.84
     Efq
    0.83
    Activations Density 1.067%

    No Known Activations