© 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. 40-GEMMASCOPE-RES-16K
    11. 5759
    Prev
    Next
    INDEX
    Explanations

    contractions related to possession and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.66
     CallOverrides
    -0.58
    SourceChecksum
    -0.55
    WriteTagHelper
    -0.47
    клопе
    -0.43
    BASEPATH
    -0.43
     unknownFields
    -0.43
    RTHOOK
    -0.42
     StatefulWidget
    -0.39
    RUnlock
    -0.38
    POSITIVE LOGITS
     got
    2.69
    got
    2.20
    Got
    2.09
     Got
    1.99
     GOT
    1.69
    GOT
    1.57
     gotcha
    1.19
     gotta
    1.08
    gott
    1.02
     gott
    1.00
    Activations Density 0.272%

    No Known Activations