© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27438
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating connections between thoughts or entities

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

    you followed by conjunctions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ArgsConstructor
    -0.77
    󠁢
    -0.68
    fromnode
    -0.65
    SequentialGroup
    -0.64
    NewUrlParser
    -0.63
     useContext
    -0.59
     greateſt
    -0.59
    pherals
    -0.58
     Majefty
    -0.57
     linkovi
    -0.57
    POSITIVE LOGITS
     you
    0.87
     youll
    0.83
    you
    0.59
     we
    0.57
    你就
    0.55
    makeText
    0.52
    DllImport
    0.52
     your
    0.52
     polie
    0.52
     tendrás
    0.49
    Activations Density 0.046%

    No Known Activations