© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8585
    Prev
    Next
    INDEX
    Explanations

    the preposition "by" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.49
    eningrad
    -0.47
     userManager
    -0.45
    jspb
    -0.45
    complexType
    -0.44
    нгред
    -0.42
     ConstraintSet
    -0.41
     IERC
    -0.41
    løs
    -0.40
     muſt
    -0.40
    POSITIVE LOGITS
    BY
    2.88
     BY
    2.84
    By
    2.78
     By
    2.72
    by
    2.56
    bys
    1.88
     getBy
    1.77
     by
    1.77
    ByName
    1.75
    ById
    1.65
    Activations Density 0.395%

    No Known Activations