© 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. 3-GEMMASCOPE-RES-16K
    11. 9537
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    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
    ,
    -0.58
    .
    -0.53
    /
    -0.48
     or
    -0.47
     escuchado
    -0.45
     vs
    -0.45
    ;
    -0.44
    ↵↵
    -0.43
     versus
    -0.42
     duy
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.98
    parsedMessage
    0.95
    المناصب
    0.95
     InputDecoration
    0.92
    DockStyle
    0.88
    帖最后由
    0.87
    bootstrapcdn
    0.85
     surla
    0.84
    BeginContext
    0.84
     متعلقه
    0.84
    Activations Density 0.391%

    No Known Activations